We study reserve price optimization in multi-phase second price auctions, where the seller's prior actions affect the bidders' later valuations through a Markov Decision Process (MDP). Compared to the bandit setting in existing works, the setting in ours involves three challenges. First, from the seller's perspective, we need to efficiently explore the environment in the presence of potentially untruthful bidders who aim to manipulate the seller's policy. Second, we want to minimize the seller's revenue regret when the market noise distribution is unknown. Third, the seller's per-step revenue is an unknown, nonlinear random variable, and cannot even be directly observed from the environment but realized values. We propose a mechanism addressing all three challenges. To address the first challenge, we use a combination of a new technique named “buffer periods” and inspirations from Reinforcement Learning (RL) with low switching cost to limit bidders' surplus from untruthful bidding, thereby incentivizing approximately truthful bidding. The second one is tackled by a novel algorithm that removes the need for pure exploration when the market noise distribution is unknown. The third challenge is resolved by an extension of LSVI-UCB, where we use the auction's underlying structure to control the uncertainty of the revenue function. The three techniques culminate in the \underline{C}ontextual-\underline{L}SVI-\underline{U}CB-\underline{B}uffer (CLUB) algorithm which achieves $\tilde{\mathcal{O}}(H^{5/2}\sqrt{K})$ revenue regret, where $K$ is the number of episodes and $H$ is the length of each episode, when the market noise is known and $\tilde{\mathcal{O}}(H^{3}\sqrt{K})$ revenue regret when the noise is unknown with no assumptions on bidders' truthfulness.

In safety-critical robot planning or control, manually specifying safety constraints or learning them from demonstrations can be challenging. In this article, we propose a certifiable alignment method for a robot to learn a safety constraint in its model predictive control (MPC) policy with human online directional feedback. To our knowledge, it is the first method to learn safety constraints from human feedback. The proposed method is based on an empirical observation: human directional feedback, when available, tends to guide the robot toward safer regions. The method only requires the direction of human feedback to update the learning hypothesis space. It is certifiable, providing an upper bound on the total number of human feedback in the case of successful learning, or declaring the hypothesis misspecification, i.e., the true implicit safety constraint cannot be found within the specified hypothesis space. We evaluated the proposed method using numerical examples and user studies in two simulation games. Additionally, we implemented and tested the proposed method on a real-world Franka robot arm performing mobile water-pouring tasks. The results demonstrate the efficacy and efficiency of our method, showing that it enables a robot to successfully learn safety constraints with a small handful (tens) of human directional corrections.

In-Context Learning (ICL) ability has been found efficient across a wide range of applications, where the Large Language Models (LLM) learn to complete the tasks from the examples in the prompt without tuning the parameters. In this work, we conduct a comprehensive study to understand ICL from a statistical perspective. First, we show that the perfectly pretrained LLMs perform Bayesian Model Averaging (BMA) for ICL under a dynamic model of examples in the prompt. The average error analysis for ICL is then built for the perfectly pretrained LLMs with the analysis of BMA. Second, we demonstrate how the attention structure boosts the BMA implementation. With sufficient examples in the prompt, attention is proven to perform BMA under the Gaussian linear ICL model, which also motivates the explicit construction of the hidden concepts from the attention heads values. Finally, we analyze the pretraining behavior of LLMs. The pretraining error is decomposed as the generalization error and the approximation error. The generalization error is upper bounded via PAC-Bayes framework. Then the ICL average error of the pretrained LLMs is shown to be the sum of $O(T^{-1})$ and the pretraining error. In addition, we analyze the ICL performance of the pretrained LLMs with misspecified examples.

Humans exhibit remarkable compositional reasoning by integrating knowledge from various sources. For example, if someone learns ( B = f(A) ) from one source and ( C = g(B) ) from another, they can deduce ( C=g(B)=g(f(A)) ) even without encountering ( ABC ) together, showcasing the generalization ability of human intelligence. In this paper, we introduce a synthetic learning task, "FTCT" (Fragmented at Training, Chained at Testing), to validate the potential of Transformers in replicating this skill and interpret its inner mechanism. During training, data consist of separated knowledge fragments from an overall causal graph. In testing, Transformers must combine these fragments to infer complete causal traces. Our findings demonstrate that few-shot Chain-of-Thought prompting enables Transformers to perform compositional reasoning on FTCT by revealing correct combinations of fragments, even if such combinations were absent in training data. Furthermore, the emergence of compositional reasoning ability is strongly correlated with model complexity and training-testing data similarity. We propose, both theoretically and empirically, that Transformers learn an underlying generalizable program from training, enabling effective compositional reasoning during testing.

Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, yet generating reliable reasoning processes remains a significant challenge. We present a unified probabilistic framework that formalizes LLM reasoning through a novel graphical model incorporating latent thinking processes and evaluation signals. Our framework addresses two critical questions: (1) how to generate high-quality reasoning processes during inference automatically, and (2) how to integrate these processes into post-training. We propose the Bootstrapping Reinforced Thinking Process (BRiTE) algorithm and demonstrate its theoretical convergence at a rate of $1/T$, where $T$ is the number of iterations. The algorithm operates in two steps. First, it generates high-quality rationales by approximating the desired posterior distribution using a reinforcement learning approach with a novel reward shaping mechanism. Second, it fine-tunes the base LLM by maximizing the joint probability of rationale generation with respect to LLM parameters. Empirical evaluation on GSM8K and MATH benchmarks demonstrates that our approach consistently improves performance across different model sizes without requiring human-annotated thinking processes, outperforming standard chain-of-thought prompting while enhancing existing post-training methods.

We develop a framework for capturing the instrumental value of data production processes, which accounts for two key factors: (a) the context of the agent’s decision-making; (b) how much data or information the buyer already possesses. We "micro-found" our data valuation function by establishing its connection to classic notions of signals and information design in economics. When instantiated in Bayesian linear regression, our value naturally corresponds to information gain. Applying our proposed data value in Bayesian linear regression for monopoly pricing, we show that if the seller can fully customize data production, she can extract the first-best revenue (i.e., full surplus) from any population of buyers, i.e., achieving first-degree price discrimination. If data can only be constructed from an existing data pool, this limits the seller’s ability to customize, and achieving first-best revenue becomes generally impossible. However, we design a mechanism that achieves seller revenue at most $\log(\kappa)$ less than the first-best, where $\kappa$ is the condition number associated with the data matrix. As a corollary, the seller extracts the first-best revenue in the multi-armed bandits special case.

Information asymmetry is a pervasive feature of multi-agent systems, especially evident in economics and social sciences. In these settings, agents tailor their actions based on private information to maximize their rewards. These strategic behaviors often introduce complexities due to confounding variables. Simultaneously, knowledge transportability poses another significant challenge, arising from the difficulties of conducting experiments in target environments. It requires transferring knowledge from environments where empirical data is more readily available. Against these backdrops, this paper explores a fundamental question in online learning: Can we employ non-i.i.d. actions to learn about confounders even when requiring knowledge transfer? We present a sample-efficient algorithm designed to accurately identify system dynamics under information asymmetry and to navigate the challenges of knowledge transfer effectively in reinforcement learning, framed within an online strategic interaction model. Our method provably achieves learning of an $\epsilon$-optimal policy with a tight sample complexity of $\tilde{O}(1/\epsilon^2)$.

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often overlook the qualitative aspects of responses, despite having access to preference data that includes reward scores from judge models during AI feedback. Striving to maximize the implicit reward gap between the chosen and the slightly inferior rejected responses can cause overfitting and unnecessary unlearning of the high-quality rejected responses. The unawareness of the reward scores also drives the LLM to indiscriminately favor the low-quality chosen responses and fail to generalize to optimal responses that are sparse in data. To overcome these shortcomings, our study introduces reward-conditioned LLM policies that discern and learn from the entire spectrum of response quality within the dataset, helping extrapolate to more optimal regions. We propose an effective yet simple data relabeling method that conditions the preference pairs on quality scores to construct a reward-augmented dataset. The experiments across various benchmarks and diverse models demonstrate that our approach consistently boosts DPO by a considerable margin. Through comprehensive ablation studies, we demonstrate that our method not only maximizes the utility of preference data but also mitigates the issue of unlearning, demonstrating its broad effectiveness beyond mere data expansion. Our code is available at https://github.com/shenao-zhang/reward-augmented-preference.

Object-goal navigation requires mobile robots to efficiently locate targets with visual and spatial information, yet existing methods struggle with generalization in unseen environments. Heuristic approaches with naive metrics fail in complex layouts, while graph-based and learning-based methods suffer from environmental biases and limited generalization. Although Large Language Models (LLMs) as planners or agents offer a rich knowledge base, they are cost-inefficient and lack targeted historical experience. To address these challenges, we propose the LLM-enhanced Object Affinities Transfer (LOAT) framework, integrating LLM-derived semantics with learning-based approaches to leverage experiential object affinities for better generalization in unseen settings. LOAT employs a dual-module strategy: one module accesses LLMs’ vast knowledge, and the other applies learned object semantic relationships, dynamically fusing these sources based on context. Evaluations in AI2-THOR and Habitat simulators show significant improvements in navigation success and efficiency, and real-world deployment demonstrates the zero-shot ability of LOAT to enhance object-goal navigation systems.

Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs. Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary. In this paper, we introduce a communication regime named CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. Specifically, we remove the token sampling step from LLMs and let them communicate their beliefs across the vocabulary through the expectation of the raw transformer output embeddings. Remarkably, by deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights, outperforming the state-of-the-art LLM debate methods using natural language by 0.5-5.0% across five reasoning tasks and multiple open-source LLMs of varying sizes. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs. We anticipate that CIPHER will inspire further exploration for the design of interactions within LLM agent systems, offering a new direction that could significantly influence future developments in the field.

We study multi-agent reinforcement learning (MARL) for the general-sum Markov Games (MGs) under general function approximation. In order to find the minimum assumption for sample-efficient learning, we introduce a novel complexity measure called the Multi-Agent Decoupling Coefficient (MADC) for general-sum MGs. Using this measure, we propose the first unified algorithmic framework that ensures sample efficiency in learning Nash Equilibrium, Coarse Correlated Equilibrium, and Correlated Equilibrium for both model-based and model-free MARL problems with low MADC. We also show that our algorithm provides comparable sublinear regret to the existing works. Moreover, our algorithm combines an equilibrium-solving oracle with a single objective optimization subprocedure that solves for the regularized payoff of each deterministic joint policy, which avoids solving constrained optimization problems within data-dependent constraints (Jin et al. 2020; Wang et al. 2023) or executing sampling procedures with complex multi-objective optimization problems (Foster et al. 2023), thus being more amenable to empirical implementation.

Recent advancements in differentiable simulators highlight the potential of policy optimization using simulation gradients. Yet, these approaches are largely contingent on the continuity and smoothness of the simulation, which precludes the use of certain simulation engines, such as Mujoco. To tackle this challenge, we introduce the adaptive analytic gradient. This method views the Q function as a surrogate for future returns, consistent with the Bellman equation. By analyzing the variance of batched gradients, our method can autonomously opt for a more resilient Q function to compute the gradient when encountering rough simulation transitions. We also put forth the Adaptive-Gradient Policy Optimization (AGPO) algorithm, which leverages our proposed method for policy learning. On the theoretical side, we demonstrate AGPO’s convergence, emphasizing its stable performance under non-smooth dynamics due to low variance. On the empirical side, our results show that AGPO effectively mitigates the challenges posed by non-smoothness in policy learning through differentiable simulation.

Large language models (LLMs) demonstrate impressive reasoning abilities, but translating reasoning into actions in the real world remains challenging. In particular, it is unclear how to complete a given task provably within a minimum number of interactions with the external environment, e.g., through an internal mechanism of reasoning. To this end, we propose the first framework with provable regret guarantees to orchestrate reasoning and acting, which we call reason for future, act for now (RAFA). Specifically, we design a prompt template for reasoning that learns from the memory buffer and plans a future trajectory over a long horizon (reason for future). At each step, the LLM agent takes the initial action of the planned trajectory (act for now), stores the collected feedback in the memory buffer, and reinvokes the reasoning routine to replan the future trajectory from the new state. The key idea is to cast reasoning in LLMs as learning and planning in Bayesian adaptive Markov decision processes (MDPs). Correspondingly, we prompt LLMs with the memory buffer to estimate the unknown environment (learning) and generate an optimal trajectory for multiple future steps that maximize a value function (planning). The learning and planning subroutines are performed in an in-context manner to emulate the actor-critic update for MDPs. Our theoretical analysis establishes a $\sqrt{T}$ regret, while our experimental validation demonstrates superior empirical performance.

We take the first step in studying general sequential decision-making under two adaptivity constraints: rare policy switch and batch learning. First, we provide a general class called the Eluder Condition class, which includes a wide range of reinforcement learning classes. Then, for the rare policy switch constraint, we provide a generic algorithm to achieve a $\widetilde{\mathcal{O}}(\log K) $ switching cost with a $\widetilde{\mathcal{O}}(\sqrt{K})$ regret on the EC class. For the batch learning constraint, we provide an algorithm that provides a $\widetilde{\mathcal{O}}(\sqrt{K}+K/B)$ regret with the number of batches $B.$ This paper is the first work considering rare policy switch and batch learning under general function classes, which covers nearly all the models studied in the previous works such as tabular MDP (Bai et al. 2019, Zhang et al. 2020), linear MDP (Wang et al. 2021, Gao et al. 2021), low eluder dimension MDP (Kong et al., 2021; Velegkas et al., 2022), generalized linear function approximation (Qiao et al. 2023), and also some new classes such as the low $D_\Delta$-type Bellman eluder dimension problem, linear mixture MDP, kernelized nonlinear regulator and undercomplete partially observed Markov decision process (POMDP).

Hindsight experience replay and goal relabeling are successful in reinforcement learning (RL) since they enable agents to learn from failures. Despite their successes, we lack a theoretical understanding, such as (i) why hindsight experience replay improves sample efficiency and (ii) how to design a relabeling method that achieves sample efficiency. To this end, we construct an example to show the information-theoretical improvement in sample efficiency achieved by goal relabeling. Our example reveals that goal relabeling can enhance sample efficiency and exploit the rich information in observations through better hypothesis elimination. Based on these insights, we develop an RL algorithm called GOALIVE. To analyze the sample complexity of GOALIVE, we introduce a complexity measure, the goal-conditioned Bellman-Eluder (GOAL-BE) dimension, which characterizes the sample complexity of goal-conditioned RL problems. Compared to the Bellman-Eluder dimension, the goal-conditioned version offers an exponential improvement in the best case. To the best of our knowledge, our work provides the first characterization of the theoretical improvement in sample efficiency achieved by goal relabeling.

Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output even undesired responses. We investigate this problem in a principled manner by identifying the source of the issue as the distributional shift and uncertainty of human preference in dataset. To mitigate overoptimization, we first propose a theoretical algorithm which optimizes the policy against an adversarially chosen reward model, one that simultaneously minimizes its MLE loss and a reward penalty term. The penalty pessimistically biases the uncertain rewards so as to prevent the policy from choosing actions with spursiouly high proxy rewards, resulting in provable sample efficiency of the algorithm under a partial coverage style condition. Moving from theory to practice, the proposed algorithm further enjoys an equivalent but surprisingly easy to implement form. With a clever usage of the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines (i) a preference optimization loss that directly aligns the policy with human preference, and (ii) a supervised learning loss which explicitly imitates the policy with a baseline distribution. In the context of aligning large language models (LLM), this objective fuses the direct preference optimization (DPO) loss with the supervised fune-tuning (SFT) loss to help mitigate the overoptimization towards undesired responses, for which we name the algorithm Regularized Preference Optimization (RPO). Experiments of aligning LLMs demonstrate the improved performance of our method when compared with DPO baselines. Our work sheds light on the interplay between preference optimization and SFT in tuning LLMs with both theoretical guarantees and empirical evidence.

In offline reinforcement learning (RL) an optimal policy is learned solely from a priori collected observational data. However, in observational data, actions are often confounded by unobserved variables. Instrumental variables (IVs), in the context of RL, are the variables whose influence on the state variables is all mediated by the action. When a valid instrument is present, we can recover the confounded transition dynamics through observational data. We study a confounded Markov decision process where the transition dynamics admit an additive nonlinear functional form. Using IVs, we derive a conditional moment restriction through which we can identify transition dynamics based on observational data. We propose a provably efficient IV-aided Value Iteration (IVVI) algorithm based on a primal-dual reformulation of the conditional moment restriction. To our knowledge, this is the first provably efficient algorithm for instrument-aided offline RL.

Dynamic mechanism design studies how mechanism designers should allocate resources among agents in a time-varying environment. We consider the problem where the agents interact with the mechanism designer according to an unknown Markov Decision Process (MDP), where agent rewards and the mechanism designer's state evolve according to an episodic MDP with unknown reward functions and transition kernels. We focus on the online setting with linear function approximation and propose novel learning algorithms to recover the dynamic Vickrey-Clarke-Grove (VCG) mechanism over multiple rounds of interaction. A key contribution of our approach is incorporating reward-free online Reinforcement Learning (RL) to aid exploration over a rich policy space to estimate prices in the dynamic VCG mechanism. We show that the regret of our proposed method is upper bounded by $\tilde{\mathcal{O}}(T^{2/3})$ and further devise a lower bound to show that our algorithm is efficient, incurring the same $\Omega(T^{2 / 3})$ regret as the lower bound, where $T$ is the total number of rounds. Our work establishes the regret guarantee for online RL in solving dynamic mechanism design problems without prior knowledge of the underlying model.

We design and analyze reinforcement learning algorithms for Graphon Mean-Field Games (GMFGs). In contrast to previous works that require the precise values of the graphons, we aim to learn the Nash Equilibrium (NE) of the regularized GMFGs when the graphons are unknown. Our contributions are threefold. First, we propose the Proximal Policy Optimization for GMFG (GMFG-PPO) algorithm and show that it converges at a rate of $\tilde{O}(T^{-1/3})$ after $T$ iterations with an estimation oracle, improving on a previous work by Xie et al. (ICML, 2021). Second, using kernel embedding of distributions, we design efficient algorithms to estimate the transition kernels, reward functions, and graphons from sampled agents. Convergence rates are then derived when the positions of the agents are either known or unknown. Results for the combination of the optimization algorithm GMFG-PPO and the estimation algorithm are then provided. These algorithms are the first specifically designed for learning graphons from sampled agents. Finally, the efficacy of the proposed algorithms are corroborated through simulations. These simulations demonstrate that learning the unknown graphons reduces the exploitability effectively.

Offline reinforcement learning (RL) harnesses the power of massive datasets for resolving sequential decision problems. Most existing papers only discuss defending against out-of-distribution (OOD) actions while we investigate a broader issue, the false correlations between epistemic uncertainty and decision-making, an essential factor that causes suboptimality. In this paper, we propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL). The proposed algorithm introduces an annealing behavior cloning regularizer to help produce a high-quality estimation of uncertainty which is critical for eliminating false correlations from suboptimality. Theoretically, we justify the rationality of the proposed method and prove its convergence to the optimal policy with a sublinear rate under mild assumptions.

A key challenge in offline reinforcement learning (RL) is how to ensure the learned offline policy is safe, especially in safety-critical domains. In this article, we focus on learning a distributional value function in offline RL and optimizing a worst-case criterion of returns. However, optimizing a distributional value function in offline RL can be hard, since the crossing quantile issue is serious, and the distribution shift problem needs to be addressed. To this end, we propose monotonic quantile network (MQN) with conservative quantile regression (CQR) for risk-averse policy learning. First, we propose an MQN to learn the distribution over returns with non-crossing guarantees of the quantiles. Then, we perform CQR by penalizing the quantile estimation for out-of-distribution (OOD) actions to address the distribution shift in offline RL. Finally, we learn a worst-case policy by optimizing the conditional value-at-risk (CVaR) of the distributional value function. Furthermore, we provide theoretical analysis of the fixed-point convergence in our method. We conduct experiments in both risk-neutral and risk-sensitive offline settings, and the results show that our method obtains safe and conservative behaviors in robotic locomotion tasks.

We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market. Each household earns income and engages in consumption at each time step while aiming to maximize a concave utility subject to the underlying market conditions. The households aim to find the optimal saving strategy that maximizes their discounted cumulative utility given the market condition, while the firms determine the market conditions through maximizing corporate profit based on the household population behavior. The model captures a wide range of applications in macroeconomic studies, and we propose a data-driven reinforcement learning framework that finds the regularized competitive equilibrium of the model. The proposed algorithm enjoys theoretical guarantees in converging to the equilibrium of the market at a sub-linear rate.

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular safe RL methods such as those based on the Constrained Markov Decision Process (CMDP) paradigm formulate safety violations in a cost function and try to constrain the expectation of cumulative cost under a threshold. However, it is often difficult to effectively capture and enforce hard reachability-based safety constraints indirectly with such constraints on safety violation cost. In this work, we leverage the notion of barrier function to explicitly encode the hard safety chance constraints, and given that the environment is unknown, relax them to our design of *generative-model-based soft barrier functions*. Based on such soft barriers, we propose a novel safe RL approach with bi-level optimization that can jointly learn the unknown environment and optimize the control policy, while effectively avoiding the unsafe region with safety probability optimization. Experiments on a set of examples demonstrate that our approach can effectively enforce hard safety chance constraints and significantly outperform CMDP-based baseline methods in system safe rates measured via simulations.

Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance difference lemma that characterizes the landscape of multi-agent policy optimization, we find that the localized action value function serves as an ideal descent direction for each local policy. Motivated by the observation, we present a multi-agent PPO algorithm in which the local policy of each agent is updated similarly to vanilla PPO. We prove that with standard regularity conditions on the Markov game and problem-dependent quantities, our algorithm converges to the globally optimal policy at a sublinear rate. We extend our algorithm to the off-policy setting and introduce pessimism to policy evaluation, which aligns with experiments. To our knowledge, this is the first provably convergent multi-agent PPO algorithm in cooperative Markov games.

In this paper, we develop an approximation scheme for solving bilevel programs with equilibrium constraints, which are generally difficult to solve. Among other things, calculating the first-order derivative in such a problem requires differentiation across the hierarchy, which is computationally intensive, if not prohibitive. To bypass the hierarchy, we propose to bound such bilevel programs, equivalent to multiple-followers Stackelberg games, with two new hierarchy-free problems: a $T$-step Cournot game and a $T$-step monopoly model. Since they are standard equilibrium or optimization problems, both can be efficiently solved via first-order methods. Importantly, we show that the bounds provided by these problems — the upper bound by the $T$-step Cournot game and the lower bound by the $T$-step monopoly model — can be made arbitrarily tight by increasing the step parameter $T$ for a wide range of problems. We prove that a small $T$ usually suffices under appropriate conditions to reach an approximation acceptable for most practical purposes. Eventually, the analytical insights are highlighted through numerical examples.

Differentiable physics-based simulators have witnessed remarkable success in robot learning involving contact dynamics, benefiting from their improved accuracy and efficiency in solving the underlying complementarity problem. However, when utilizing the First-Order Policy Gradient (FOPG) method, our theory indicates that the complementarity-based systems suffer from stiffness, leading to an explosion in the gradient variance of FOPG. As a result, optimization becomes challenging due to chaotic and non-smooth loss landscapes. To tackle this issue, we propose a novel approach called Adaptive Barrier Smoothing (ABS), which introduces a class of softened complementarity systems that correspond to barrier-smoothed objectives. With a contact-aware adaptive central-path parameter, ABS reduces the FOPG gradient variance while controlling the gradient bias. We justify the adaptive design by analyzing the roots of the system’s stiffness. Additionally, we establish the convergence of FOPG and show that ABS achieves a reasonable trade-off between the gradient variance and bias by providing their upper bounds. Moreover, we present a variant of FOPG based on complementarity modeling that efficiently fits the contact dynamics by learning the physical parameters. Experimental results on various robotic tasks are provided to support our theory and method.

In reinforcement learning (RL), balancing exploration and exploitation is crucial for achieving an optimal policy in a sample-efficient way. To this end, existing sample- efficient algorithms typically consist of three components: estimation, planning, and exploration. However, to cope with general function approximators, most of them involve impractical algorithmic components to incentivize exploration, such as data-dependent level-set constraints or complicated sampling procedures. To address this challenge, we propose an easy-to-implement RL framework called Maximize to Explore (MEX), which only needs to optimize unconstrainedly a single objective that integrates the estimation and planning components while balancing exploration and exploitation automatically. Theoretically, we prove that the MEX achieves a sublinear regret with general function approximators and is extendable to the zero-sum Markov game setting. Meanwhile, we adapt deep RL baselines to design practical versions of MEX in both the model-based and model-free settings, which outperform baselines in various MuJoCo environments with sparse reward by a stable margin. Compared with existing sample-efficient algorithms with general function approximators, MEX achieves similar sample efficiency while also enjoying a lower computational cost and is more compatible with modern deep RL methods.

This paper investigates posterior sampling algorithms for competitive reinforcement learning (RL) in the context of general function approximations. Focusing on zero-sum Markov games (MGs) under two critical settings, namely self-play and adversarial learning, we first propose the self-play and adversarial generalized eluder coefficient (GEC) as complexity measures for function approximation, capturing the exploration-exploitation trade-off in MGs. Based on self-play GEC, we propose a model-based self-play posterior sampling method to control both players to learn Nash equilibrium, which can successfully handle the partial observability of states. Furthermore, we identify a set of partially observable MG models fitting MG learning with the adversarial policies of the opponent. Incorporating the adversarial GEC, we propose a model-based posterior sampling method for learning adversarial MG with potential partial observability. We further provide low regret bounds for proposed algorithms that can scale sublinearly with the proposed GEC and the number of episodes $T$. To the best of our knowledge, we for the first time develop generic model-based posterior sampling algorithms for competitive RL that can be applied to a majority of tractable zero-sum MG classes in both fully observable and partially observable MGs with self-play and adversarial learning.

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning problems, model-based RP PGMs may experience chaotic and non-smooth optimization landscapes with exploding gradient variance, which leads to slow convergence. This is in contrast to the conventional belief that reparameterization methods have low gradient estimation variance in problems such as training deep generative models. To comprehend this phenomenon, we conduct a theoretical examination of model-based RP PGMs and search for solutions to the optimization difficulties. Specifically, we analyze the convergence of the model-based RP PGMs and pinpoint the smoothness of function approximators as a major factor that affects the quality of gradient estimation. Based on our analysis, we propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls. Our experimental results demonstrate that proper normalization significantly reduces the gradient variance of model-based RP PGMs. As a result, the performance of the proposed method is comparable or superior to other gradient estimators, such as the Likelihood Ratio (LR) gradient estimator. Our code is available at https://github.com/agentification/RP_PGM.

This paper studies two fundamental problems in regularized Graphon Mean-Field Games (GMFGs). First, we establish the existence of a Nash Equilibrium (NE) of any $\lambda$-regularized GMFG (for $\lambda\geq 0$). This result relies on weaker conditions than previous works analyzing both unregularized GMFGs ($\lambda=0$) and $\lambda$-regularized MFGs, which are special cases of GMFGs. Second, we propose provably efficient algorithms to learn the NE in weakly monotone GMFGs, motivated by Lasry and Lions (2007). Previous literature either only analyzed continuous-time algorithms or required extra conditions to analyze discrete-time algorithms. In contrast, we design a discrete-time algorithm and derive its convergence rate solely under weakly monotone conditions. Furthermore, we develop and analyze the action-value function estimation procedure during the online learning process, which is absent from algorithms for monotone GMFGs. This serves as a sub-module in our optimization algorithm. The efficiency of the designed algorithm is corroborated by empirical evaluations.

We study multi-player general-sum Markov games with one of the players designated as the leader and the other players regarded as followers. In particular, we focus on the class of games where the followers are myopically rational; i.e., they aim to maximize their instantaneous rewards. For such a game, our goal is to find a Stackelberg-Nash equilibrium (SNE), which is a policy pair $(\pi^*, \nu^*)$ such that: (i) $\pi^*$ is the optimal policy for the leader when the followers always play their best response, and (ii) $\nu^*$ is the best response policy of the followers, which is a Nash equilibrium of the followers' game induced by $\pi^*$. We develop sample-efficient reinforcement learning (RL) algorithms for solving for an SNE in both online and offline settings. Our algorithms are optimistic and pessimistic variants of least-squares value iteration, and they are readily able to incorporate function approximation tools in the setting of large state spaces. Furthermore, for the case with linear function approximation, we prove that our algorithms achieve sublinear regret and suboptimality under online and offline setups respectively. To the best of our knowledge, we establish the first provably efficient RL algorithms for solving for SNEs in general-sum Markov games with myopically rational followers.

We study the Constrained Convex Markov Decision Process (MDP), where the goal is to minimize a convex functional of the visitation measure, subject to a convex constraint. Designing algorithms for a constrained convex MDP faces several challenges, including (1) handling the large state space, (2) managing the exploration/exploitation tradeoff, and (3) solving the constrained optimization where the objective and the constraint are both nonlinear functions of the visitation measure. In this work, we present a model-based algorithm, Variational Primal-Dual Policy Optimization (VPDPO), in which Lagrangian and Fenchel duality are implemented to reformulate the original constrained problem into an unconstrained primal-dual optimization. The primal variables are updated by model-based value iteration following the principle of Optimism in the Face of Uncertainty (OFU), while the dual variables are updated by gradient ascent. Moreover, by embedding the visitation measure into a finite-dimensional space, we can handle large state spaces by incorporating function approximation. Two notable examples are (1) Kernelized Nonlinear Regulators and (2) Low-rank MDPs. We prove that with an optimistic planning oracle, our algorithm achieves sublinear regret and constraint violation in both cases and can attain the globally optimal policy of the original constrained problem.

Multigoal reinforcement learning (RL) extends the typical RL with goal-conditional value functions and policies. One efficient multigoal RL algorithm is the hindsight experience replay (HER). By treating a hindsight goal from failed experiences as the original goal, HER enables the agent to receive rewards frequently. However, a key assumption of HER is that the hindsight goals do not change the likelihood of the sampled transitions and trajectories used in training, which is not the fact according to our analysis. More specifically, we show that using hindsight goals changes such a likelihood and results in a biased learning objective for multigoal RL. We analyze the hindsight bias due to this use of hindsight goals and propose the bias-corrected HER (BHER), an efficient algorithm that corrects the hindsight bias in training. We further show that BHER outperforms several state-of-the-art multigoal RL approaches in challenging robotics tasks.

Efficient exploration remains a challenging problem in reinforcement learning, especially for tasks where extrinsic rewards from environments are sparse or even totally disregarded. Significant advances based on intrinsic motivation show promising results in simple environments but often get stuck in environments with multimodal and stochastic dynamics. In this work, we propose a variational dynamic model based on the conditional variational inference to model the multimodality and stochasticity. We consider the environmental state-action transition as a conditional generative process by generating the next-state prediction under the condition of the current state, action, and latent variable, which provides a better understanding of the dynamics and leads to a better performance in exploration. We derive an upper bound of the negative log likelihood of the environmental transition and use such an upper bound as the intrinsic reward for exploration, which allows the agent to learn skills by self-supervised exploration without observing extrinsic rewards. We evaluate the proposed method on several image-based simulation tasks and a real robotic manipulating task. Our method outperforms several state-of-the-art environment model-based exploration approaches.

As one of the most popular methods in the field of reinforcement learning, Q-learning has received increasing attention. Recently, there have been more theoretical works on the regret bound of algorithms that belong to the Q-learning class in different settings. In this paper, we analyze the cumulative regret when conducting Nash Q-learning algorithm on 2-player turn-based stochastic Markov games (2-TBSG), and propose the very first gap dependent logarithmic upper bounds in the episodic tabular setting. This bound matches the theoretical lower bound only up to a logarithmic term. Furthermore, we extend the conclusion to the discounted game setting with infinite horizon and propose a similar gap dependent logarithmic regret bound. Also, under the linear MDP assumption, we obtain another logarithmic regret for 2-TBSG, in both centralized and independent settings.

In the current control design of safety-critical cyber-physical systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However, due to the increasing system complexity and the fundamental hardness of designing a controller with formal guarantees, such an open-loop process of design-then-verify often results in many iterations and fails to provide the necessary guarantees. In this paper, we propose a correct-by-construction control learning framework that integrates the verification into the control design process in a closed-loop manner, i.e., design-while-verify. Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching. We formulate an optimization problem based on such metrics for tuning the controller parameters, and develop an approximated gradient descent algorithm with a difference method to solve the optimization problem and learn the controller. The learned controller is formally guaranteed to meet the required reach-avoid property. By treating verifiability as a first-class objective and effectively leveraging the verification results during the control learning process, our approach can significantly improve the chance of finding a control design with formal property guarantees, demonstrated in a set of experiments that use model-based or neural network based controllers.

We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial observability and function approximation for a class of POMDPs with a linear structure. In detail, we propose a reinforcement learning algorithm (Optimistic Exploration via Adversarial Integral Equation or OP-TENET) that attains an $\epsilon$-optimal policy within $O(1/\epsilon^2)$ episodes. In particular, the sample complexity scales polynomially in the intrinsic dimension of the linear structure and is independent of the size of the observation and state spaces. The sample efficiency of OP-TENET is enabled by a sequence of ingredients: (i) a Bellman operator with finite memory, which represents the value function in a recursive manner, (ii) the identification and estimation of such an operator via an adversarial integral equation, which features a smoothed discriminator tailored to the linear structure, and (iii) the exploration of the observation and state spaces via optimism, which is based on quantifying the uncertainty in the adversarial integral equation.

In a Markov decision process (MDP), an agent interacts with the environment via perceptions and actions. During this process, the agent aims to maximize its own gain. Hence, appropriate regulations are often required, if we hope to take the external costs/benefits of its actions into consideration. In this paper, we study how to regulate such an agent by redesigning model parameters that can affect the rewards and/or the transition kernels. We formulate this problem as a bilevel program, in which the lower-level MDP is regulated by the upper-level model designer. To solve the resulting problem, we develop a scheme that allows the designer to iteratively predict the agent’s reaction by solving the MDP and then adaptively update model parameters based on the predicted reaction. The algorithm is first theoretically analyzed and then empirically tested on several MDP models arising in economics and robotics.

We study human-in-the-loop reinforcement learning (RL) with trajectory preferences, where instead of receiving a numeric reward at each step, the RL agent only receives preferences over trajectory pairs from a human overseer. The goal of the RL agent is to learn the optimal policy which is most preferred by the human overseer. Despite the empirical success in various real-world applications, the theoretical understanding of preference-based RL (PbRL) is only limited to the tabular case. In this paper, we propose the first optimistic model-based algorithm for PbRL with general function approximation, which estimates the model using value-targeted regression and calculates the exploratory policies by solving an optimistic planning problem. We prove that our algorithm achieves the regret bound of $\tilde{O} (\operatorname{poly}(d H) \sqrt{K} )$, where $d$ is the complexity measure of the transition and preference model depending on the Eluder dimension and log-covering numbers, $H$ is the planning horizon, $K$ is the number of episodes, and $\tilde O(\cdot)$ omits logarithmic terms. Our lower bound indicates that our algorithm is near-optimal when specialized to the linear setting. Furthermore, we extend the PbRL problem by formulating a novel problem called RL with $n$-wise comparisons, and provide the first sample-efficient algorithm for this new setting. To the best of our knowledge, this is the first theoretical result for PbRL with (general) function approximation.

We study offline reinforcement learning (RL) for partially observable Markov decision processes (POMDPs) with possibly infinite state and observation spaces. Under the undercompleteness assumption, the optimal policy in such POMDPs are characterized by a class of finite-memory Bellman operators. In the offline setting, estimating these operators directly is challenging due to (i) the large observation space and (ii) insufficient coverage of the offline dataset. To tackle these challenges, we propose a novel algorithm that constructs confidence regions for these Bellman operators via offline estimation of their RKHS embeddings, and returns the final policy via pessimistic planning within the confidence regions. We prove that the proposed algorithm attains an \(\epsilon\)-optimal policy using an offline dataset containing \(\tilde\cO(1 / \epsilon^2)\){episodes}, provided that the behavior policy has good coverage over the optimal trajectory. To our best knowledge, our algorithm is the first provably sample efficient offline algorithm for POMDPs without uniform coverage assumptions.

We study a bilevel economic system, which we refer to as a Markov exchange economy (MEE), from the point of view of multi-agent reinforcement learning (MARL). An MEE involves a central planner and a group of self-interested agents. The goal of the agents is to form a Competitive Equilibrium (CE), where each agent myopically maximizes her own utility at each step. The goal of the central planner is to steer the system so as to maximize social welfare, which is defined as the sum of the utilities of all agents. Working in a setting in which the utility function and the system dynamics are both unknown, we propose to find the socially optimal policy and the CE from data via both online and offline variants of MARL. Concretely, we first devise a novel suboptimality metric specifically tailored to MEE, such that minimizing such a metric certifies globally optimal policies for both the planner and the agents. Second, in the online setting, we propose an algorithm, dubbed as \texttt{MOLM}, which combines the optimism principle for exploration with subgame CE seeking. Our algorithm can readily incorporate general function approximation tools for handling large state spaces and achieves a sublinear regret. Finally, we adapt the algorithm to an offline setting based on the pessimism principle and establish an upper bound on the suboptimality.

In generative adversarial imitation learning (GAIL), the agent aims to learn a policy from an expert demonstration so that its performance cannot be discriminated from the expert policy on a certain predefined reward set. In this paper, we study GAIL in both online and offline settings with linear function approximation, where both the transition and reward function are linear in the feature maps. Besides the expert demonstration, in the online setting the agent can interact with the environment, while in the offline setting the agent only accesses an additional dataset collected by a prior. For online GAIL, we propose an optimistic generative adversarial policy imitation algorithm (OGAPI) and prove that OGAPI achieves $\widetilde{\mathcal{O}}(\sqrt{H^4d^3K}+\sqrt{H^3d^2K^2/N_1})$ regret. Here $N_1$ represents the number of trajectories of the expert demonstration, $d$ is the feature dimension, and $K$ is the number of episodes. For offline GAIL, we propose a pessimistic generative adversarial policy imitation algorithm (PGAPI). We also obtain the optimality gap of PGAPI, achieving the minimax lower bound in the utilization of the additional dataset. Assuming sufficient coverage on the additional dataset, we show that PGAPI achieves $\widetilde{\mathcal{O}}(\sqrt{H^4d^2/K}+\sqrt{H^4d^3/N_2}+\sqrt{H^3d^2/N_1})$ optimality gap. Here $N_2$ represents the number of trajectories of the additional dataset with sufficient coverage.

Dynamic mechanism design has garnered significant attention from both computer scientists and economists in recent years. By allowing agents to interact with the seller over multiple rounds, where agents’ reward functions may change with time and are state-dependent, the framework is able to model a rich class of real-world problems. In these works, the interaction between agents and sellers is often assumed to follow a Markov Decision Process (MDP). We focus on the setting where the reward and transition functions of such an MDP are not known a priori, and we are attempting to recover the optimal mechanism using an a priori collected data set. In the setting where the function approximation is employed to handle large state spaces, with only mild assumptions on the expressiveness of the function class, we are able to design a dynamic mechanism using offline reinforcement learning algorithms. Moreover, learned mechanisms approximately have three key desiderata: efficiency, individual rationality, and truthfulness. Our algorithm is based on the pessimism principle and only requires a mild assumption on the coverage of the offline data set. To the best of our knowledge, our work provides the first offline RL algorithm for dynamic mechanism design without assuming uniform coverage.

In view of its power in extracting feature representation, contrastive self-supervised learning has been successfully integrated into the practice of (deep) reinforcement learning (RL), leading to efficient policy learning on various applications. Despite its tremendous empirical successes, the understanding of contrastive learning for RL remains elusive. To narrow such a gap, we study contrastive-learning empowered RL for a class of Markov decision processes (MDPs) and Markov games (MGs) with low-rank transitions. For both models, we propose to extract the correct feature representations of the low-rank model by minimizing a contrastive loss. Moreover, under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs. We further theoretically prove that our algorithm recovers the true representations and simultaneously achieves sample efficiency in learning the optimal policy and Nash equilibrium in MDPs and MGs. We also provide empirical studies to demonstrate the efficacy of the UCB-based contrastive learning method for RL. To the best of our knowledge, we provide the first provably efficient online RL algorithm that incorporates contrastive learning for representation learning.

We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori. When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving. We propose a pessimism-based algorithm, dubbed as pessimistic minimax value iteration (PMVI), which overcomes the distributional shift by constructing pessimistic estimates of the value functions for both players and outputs a policy pair by solving a correlated coarse equilibrium based on the two value functions. Furthermore, we establish a data-dependent upper bound on the suboptimality which recovers a sublinear rate without the assumption on uniform coverage of the dataset. We also prove an information-theoretical lower bound, which shows our upper bound is nearly minimax optimal, which suggests that the data-dependent term is intrinsic. Our theoretical results also highlight a notion of “relative uncertainty”, which characterizes the necessary and sufficient condition for achieving sample efficiency in offline MGs. To the best of our knowledge, we provide the first nearly minimax optimal result for offline MGs with function approximation.

We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded and known. SMRL uses score matching, an unnormalized density estimation technique that enables efficient estimation of the model parameter by ridge regression. Under standard regularity assumptions, SMRL achieves $\tilde O(d\sqrt{H^3T})$ online regret, where $H$ is the length of each episode and $T$ is the total number of interactions (ignoring polynomial dependence on structural scale parameters).

To regulate a social system comprised of self-interested agents, economic incentives are often required to induce a desirable outcome. This incentive design problem naturally possesses a bilevel structure, in which a designer modifies the payoffs of the agents with incentives while anticipating the response of the agents, who play a non-cooperative game that converges to an equilibrium. The existing bilevel optimization algorithms raise a dilemma when applied to this problem: anticipating how incentives affect the agents at equilibrium requires solving the equilibrium problem repeatedly, which is computationally inefficient; bypassing the time-consuming step of equilibrium-finding can reduce the computational cost, but may lead the designer to a sub-optimal solution. To address such a dilemma, we propose a method that tackles the designer’s and agents’ problems simultaneously in a single loop. Specifically, at each iteration, both the designer and the agents only move one step. Nevertheless, we allow the designer to gradually learn the overall influence of the incentives on the agents, which guarantees optimality after convergence. The convergence rate of the proposed scheme is also established for a broad class of games.

Finance is a particularly challenging playground for deep reinforcement learning. However, establishing high-quality market environments and benchmarks for financial reinforcement learning is challenging due to three major factors, namely, low signal-to-noise ratio of financial data, survivorship bias of historical data, and backtesting overfitting. In this paper, we present an openly accessible FinRL-Meta library that has been actively maintained by the AI4Finance community. First, following a DataOps paradigm, we will provide hundreds of market environments through an automatic data curation pipeline that processes dynamic datasets from real-world markets into gym-style market environments. Second, we reproduce popular papers as stepping stones for users to design new trading strategies. We also deploy the library on cloud platforms so that users can visualize their own results and assess the relative performance via community-wise competitions. Third, FinRL-Meta provides tens of Jupyter/Python demos organized into a curriculum and a documentation website to serve the rapidly growing community. FinRL-Meta is available at: \url{https://github.com/AI4Finance-Foundation/FinRL-Meta}

We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market.At each step, the agents are presented with a dynamical context, where the contexts determine the utilities. The planner controls the transition of the contexts to maximize the cumulative social welfare, while the agents aim to find a myopic stable matching at each step. Such a setting captures a range of applications including ridesharing platforms. We formalize the problem by proposing a reinforcement learning framework that integrates optimistic value iteration with maximum weight matching. The proposed algorithm addresses the coupled challenges of sequential exploration, matching stability, and function approximation. We prove that the algorithm achieves sublinear regret.

General Value Function (GVF) is a powerful tool to represent both the {\em predictive} and {\em retrospective} knowledge in reinforcement learning (RL). In practice, often multiple interrelated GVFs need to be evaluated jointly with pre-collected off-policy samples. In the literature, the gradient temporal difference (GTD) learning method has been adopted to evaluate GVFs in the off-policy setting, but such an approach may suffer from a large estimation error even if the function approximation class is sufficiently expressive. Moreover, none of the previous work have formally established the convergence guarantee to the ground truth GVFs under the function approximation settings. In this paper, we address both issues through the lens of a class of GVFs with causal filtering, which cover a wide range of RL applications such as reward variance, value gradient, cost in anomaly detection, stationary distribution gradient, etc. We propose a new algorithm called GenTD for off-policy GVFs evaluation and show that GenTD learns multiple interrelated multi-dimensional GVFs as efficiently as a single canonical scalar value function. We further show that unlike GTD, the learned GVFs by GenTD are guaranteed to converge to the ground truth GVFs as long as the function approximation power is sufficiently large. To our best knowledge, GenTD is the first off-policy GVF evaluation algorithm that has global optimality guarantee.

Offline reinforcement learning (RL) provides a promising direction to exploit massive amount of offline data for complex decision-making tasks. Due to the distribution shift issue, current offline RL algorithms are generally designed to be conservative in value estimation and action selection. However, such conservatism can impair the robustness of learned policies when encountering observation deviation under realistic conditions, such as sensor errors and adversarial attacks. To trade off robustness and conservatism, we propose Robust Offline Reinforcement Learning (RORL) with a novel conservative smoothing technique. In RORL, we explicitly introduce regularization on the policy and the value function for states near the dataset, as well as additional conservative value estimation on these states. Theoretically, we show RORL enjoys a tighter suboptimality bound than recent theoretical results in linear MDPs. We demonstrate that RORL can achieve state-of-the-art performance on the general offline RL benchmark and is considerably robust to adversarial observation perturbations.

The cooperative Multi-Agent Reinforcement Learning (MARL) with permutation invariant agents framework has achieved tremendous empirical successes in real-world applications. Unfortunately, the theoretical understanding of this MARL problem is lacking due to the curse of many agents and the limited exploration of the relational reasoning in existing works. In this paper, we verify that the transformer implements complex relational reasoning, and we propose and analyze model-free and model-based offline MARL algorithms with the transformer approximators. We prove that the suboptimality gaps of the model-free and model-based algorithms are independent of and logarithmic in the number of agents respectively, which mitigates the curse of many agents. These results are consequences of a novel generalization error bound of the transformer and a novel analysis of the Maximum Likelihood Estimate (MLE) of the system dynamics with the transformer. Our model-based algorithm is the first provably efficient MARL algorithm that explicitly exploits the permutation invariance of the agents. Our improved generalization bound may be of independent interest and is applicable to other regression problems related to the transformer beyond MARL.

In today's economy, it becomes important for Internet platforms to consider the sequential information design problem to align its long term interest with incentives of the gig service providers (e.g., drivers, hosts). This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs), in which a sender, with informational advantage, seeks to persuade a stream of myopic receivers to take actions that maximize the sender's cumulative utilities in a finite horizon Markovian environment with varying prior and utility functions. Planning in MPPs thus faces the unique challenge in finding a signaling policy that is simultaneously persuasive to the myopic receivers and inducing the optimal long-term cumulative utilities of the sender. Nevertheless, in the population level where the model is known, it turns out that we can efficiently determine the optimal (resp. ε-optimal) policy with finite (resp. infinite) states and outcomes, through a modified formulation of the Bellman equation that additionally takes persuasiveness into consideration.

We study the safe reinforcement learning problem using the constrained Markov decision processes in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value of a utility function. We focus on an episodic setting with the function approximation where the Markov transition kernels have a linear structure but do not impose any additional assumptions on the sampling model. Designing safe reinforcement learning algorithms with provable computational and statistical efficiency is particularly challenging under this setting because of the need to incorporate both the safety constraint and the function approximation into the fundamental exploitation/exploration tradeoff. To this end, we present an \underline{O}ptimistic \underline{P}rimal-\underline{D}ual Proximal Policy \underline{OP}timization \mbox{(OPDOP)} algorithm where the value function is estimated by combining the least-squares policy evaluation and an additional bonus term for safe exploration. We prove that the proposed algorithm achieves an $\tilde{O}(d H^{2.5}\sqrt{T})$ regret and an $\tilde{O}(d H^{2.5}\sqrt{T})$ constraint violation, where $d$ is the dimension of the feature mapping, $H$ is the horizon of each episode, and $T$ is the total number of steps. These bounds hold when the reward/utility functions are fixed but the feedback after each episode is bandit. Our bounds depend on the capacity of the state-action space only through the dimension of the feature mapping and thus our results hold even when the number of states goes to infinity. To the best of our knowledge, we provide the first provably efficient online policy optimization algorithm for constrained Markov decision processes in the function approximation setting, with safe exploration.

It is important to collect credible training samples $(x,y)$ for building data-intensive learning systems (e.g., a deep learning system). Asking people to report complex distribution $p(x)$, though theoretically viable, is challenging in practice. This is primarily due to the cognitive loads required for human agents to form the report of this highly complicated information. While classical elicitation mechanisms apply to eliciting a complex and generative (and continuous) distribution $p(x)$, we are interested in eliciting samples $x_i \sim p(x)$ from agents directly. We coin the above problem sample elicitation. This paper introduces a deep learning aided method to incentivize credible sample contributions from self-interested and rational agents. We show that with an accurate estimation of a certain $f$-divergence function we can achieve approximate incentive compatibility in eliciting truthful samples. We then present an efficient estimator with theoretical guarantees via studying the variational forms of the $f$-divergence function. We also show a connection between this sample elicitation problem and $f$-GAN, and how this connection can help reconstruct an estimator of the distribution based on collected samples. Experiments on synthetic data, MNIST, and CIFAR-10 datasets demonstrate that our mechanism elicits truthful samples. Our implementation is available at https://github.com/weijiaheng/Credible-sample-elicitation.git.

Risk-sensitivity plays a central role in artificial intelligence safety. In this paper, we study the global convergence of the actor-critic algorithm for risk-sensitive reinforcement learning (RSRL) with exponential utility, which remains challenging for policy optimization as it lacks the linearity needed to formulate policy gradient. To bypass such an issue of nonlinearity, we resort to the equivalence between RSRL and robust adversarial reinforcement learning (RARL), which is formulated as a zero-sum Markov game with a hypothetical adversary. In particular, the Nash equilibrium (NE) of such a game yields the optimal policy for RSRL, which is provably robust. We focus on a simple yet fundamental setting known as linear-quadratic (LQ) game. To attain the optimal policy, we develop a nested natural actor-critic algorithm, which provably converges to the NE of the LQ game at a sublinear rate, thus solving both RSRL and RARL. To the best knowledge, the proposed nested actor-critic algorithm appears to be the first model-free policy optimization algorithm that provably attains the optimal policy for RSRL and RARL in the LQ setting, which sheds light on more general settings.

Neural networks are being increasingly applied to control and decision making for learning-enabled cyber-physical systems (LE-CPSs). They have shown promising performance without requiring the development of complex physical models; however, their adoption is significantly hindered by the concerns on their safety, robustness, and efficiency. In this work, we propose COCKTAIL, a novel design framework that automatically learns a neural network based controller from multiple existing control methods (experts) that could be either model-based or neural network based. In particular, COCKTAIL first performs reinforcement learning to learn an optimal system-level adaptive mixing strategy that incorporates the underlying experts with dynamically-assigned weights, and then conducts a teacher-student distillation with probabilistic adversarial training and regularization to synthesize a student neural network controller with improved control robustness (measured by a safe control rate metric with respect to adversarial attacks or measurement noises), control energy efficiency, and verifiability (measured by the computation time for verification). Experiments on three non-linear systems demonstrate significant advantages of our approach on these properties over various baseline methods.

One principled approach for provably efficient exploration is incorporating the upper confidence bound (UCB) into the value function as a bonus. However, UCB is specified to deal with linear and tabular settings and is incompatible with Deep Reinforcement Learning (DRL). In this paper, we propose a principled exploration method for DRL through Optimistic Bootstrapping and Backward Induction (OB2I). OB2I constructs a general-purpose UCB-bonus through non-parametric bootstrap in DRL. The UCB-bonus estimates the epistemic uncertainty of state-action pairs for optimistic exploration. We build theoretical connections between the proposed UCB-bonus and the LSVI-UCB in linear setting. We propagate future uncertainty in a time-consistent manner through episodic backward update, which exploits the theoretical advantage and empirically improves the sample-efficiency. Our experiments in MNIST maze and Atari suit suggest that OB2I outperforms several state-of-the-art exploration approaches.

We study function approximation for episodic reinforcement learning with entropic risk measure. We first propose an algorithm with linear function approximation. Compared to existing algorithms, which suffer from improper regularization and regression biases, this algorithm features debiasing transformations in backward induction and regression procedures. We further propose an algorithm with general function approximation, which features implicit debiasing transformations. We prove that both algorithms achieve a sublinear regret and demonstrate a trade-off between generality and efficiency. Our analysis provides a unified framework for function approximation in risk-sensitive reinforcement learning, which leads to the first sublinear regret bounds in the setting.

We study the global convergence and global optimality of the actor-critic algorithm applied for the zero-sum two-player stochastic games in a decentralized manner. We focus on the single-timescale setting where the critic is updated by applying the Bellman operator only once and the actor is updated by policy gradient with the information from the critic. Our algorithm is in a decentralized manner, as we assume that each player has no access to the actions of the other one, which, in a way, protects the privacy of both players. Moreover, we consider linear function approximations for both actor and critic, and we prove that the sequence of joint policy generated by our decentralized linear algorithm converges to the minimax equilibrium at a sublinear rate \(\cO(\sqrt{K})\), where \(K\){is} the number of iterations. To the best of our knowledge, we establish the global optimality and convergence of decentralized actor-critic algorithm on zero-sum two-player stochastic games with linear function approximations for the first time.

We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches, which are often computationally intractable, our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. To attain optimistic value function estimation without resorting to a UCB-style bonus, we introduce an optimistic reward sampling procedure. When the value functions can be represented by a function class $\mathcal{F}$, our algorithm achieves a worst-case regret bound of $\tilde{O}(\mathrm{poly}(d_EH)\sqrt{T})$ where $T$ is the time elapsed, $H$ is the planning horizon and $d_E$ is the \emph{eluder dimension} of $\mathcal{F}$. In the linear setting, our algorithm reduces to LSVI-PHE, a variant of RLSVI, that enjoys an $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret. We complement the theory with an empirical evaluation across known difficult exploration tasks.

We study offline reinforcement learning (RL), which aims to learn an optimal policy based on a dataset collected a priori. Due to the lack of further interactions with the environment, offline RL suffers from the insufficient coverage of the dataset, which eludes most existing theoretical analysis. In this paper, we propose a pessimistic variant of the value iteration algorithm (PEVI), which incorporates an uncertainty quantifier as the penalty function. Such a penalty function simply flips the sign of the bonus function for promoting exploration in online RL, which makes it easily implementable and compatible with general function approximators. Without assuming the sufficient coverage of the dataset, we establish a data-dependent upper bound on the suboptimality of PEVI for general Markov decision processes (MDPs). When specialized to linear MDPs, it matches the information-theoretic lower bound up to multiplicative factors of the dimension and horizon. In other words, pessimism is not only provably efficient but also minimax optimal. In particular, given the dataset, the learned policy serves as the “best effort” among all policies, as no other policies can do better. Our theoretical analysis identifies the critical role of pessimism in eliminating a notion of spurious correlation, which emerges from the “irrelevant” trajectories that are less covered by the dataset and not informative for the optimal policy.

Game optimization has been extensively studied when decision variables lie in a finite-dimensional space, of which solutions correspond to pure strategies at the Nash equilibrium (NE), and the gradient descent-ascent (GDA) method works widely in practice. In this paper, we consider infinite-dimensional zero-sum games by a min-max distributional optimization problem over a space of probability measures defined on a continuous variable set, which is inspired by finding a mixed NE for finite-dimensional zero-sum games. We then aim to answer the following question: \textit{Will GDA-type algorithms still be provably efficient when extended to infinite-dimensional zero-sum games?} To answer this question, we propose a particle-based variational transport algorithm based on GDA in the functional spaces. Specifically, the algorithm performs multi-step functional gradient descent-ascent in the Wasserstein space via pushing two sets of particles in the variable space. By characterizing the gradient estimation error from variational form maximization and the convergence behavior of each player with different objective landscapes, we prove rigorously that the generalized GDA algorithm converges to the NE or the value of the game efficiently for a class of games under the Polyak-Ł{ojasiewicz} (PL) condition. To conclude, we provide complete statistical and convergence guarantees for solving an infinite-dimensional zero-sum game via a provably efficient particle-based method. Additionally, our work provides the first thorough statistical analysis for the particle-based algorithm to learn an objective functional with a variational form using universal approximators (\textit{i.e.}, neural networks (NNs)), which is of independent interest.

While single-agent policy optimization in a fixed environment has attracted a lot of research attention recently in the reinforcement learning community, much less is known theoretically when there are multiple agents playing in a potentially competitive environment. We take steps forward by proposing and analyzing new fictitious play policy optimization algorithms for two-player zero-sum Markov games with structured but unknown transitions. We consider two classes of transition structures: factored independent transition and single-controller transition. For both scenarios, we prove tight $\widetilde{\mathcal{O}}(\sqrt{T})$ regret bounds after $T$ steps in a two-agent competitive game scenario. The regret of each player is measured against a potentially adversarial opponent who can choose a single best policy in hindsight after observing the full policy sequence. Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization in a non-stationary environment. When both players adopt the proposed algorithms, their overall optimality gap is $\widetilde{\mathcal{O}}(\sqrt{T})$.

To achieve sample efficiency in reinforcement learning (RL), it necessitates to efficiently explore the underlying environment. Under the offline setting, addressing the exploration challenge lies in collecting an offline dataset with sufficient coverage. Motivated by such a challenge, we study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. Then, given any extrinsic reward, the agent computes the optimal policy via offline RL with data collected in the exploration stage. Moreover, we tackle this problem under the context of function approximation, leveraging powerful function approximators. Specifically, we propose to explore via an optimistic variant of the value-iteration algorithm incorporating kernel and neural function approximations, where we adopt the associated exploration bonus as the exploration reward. Moreover, we design exploration and planning algorithms for both single-agent MDPs and zero-sum Markov games and prove that our methods can achieve $\widetilde{\mathcal{O}}(1 /\varepsilon^2)$ sample complexity for generating a $\varepsilon$-suboptimal policy or $\varepsilon$-approximate Nash equilibrium when given an arbitrary extrinsic reward. To the best of our knowledge, we establish the first provably efficient reward-free RL algorithm with kernel and neural function approximators.

Recent years have witnessed the success of multi-agent reinforcement learning, which has motivated new research directions for mean-field control (MFC) and mean-field game (MFG), as the multi-agent system can be well approximated by a mean-field problem when the number of agents grows to be very large. In this paper, we study the policy gradient (PG) method for the linear-quadratic mean-field control and game, where we assume each agent has identical linear state transitions and quadratic cost functions. While most recent works on policy gradient for MFC and MFG are based on discrete-time models, we focus on a continuous-time model where some of our analyzing techniques could be valuable to the interested readers. For both the MFC and the MFG, we provide PG update and show that it converges to the optimal solution at a linear rate, which is verified by a synthetic simulation. For the MFG, we also provide sufficient conditions for the existence and uniqueness of the Nash equilibrium.

We study reinforcement learning in mean-field games. To achieve the Nash equilibrium, which consists of a policy and a mean-field state, existing algorithms require obtaining the optimal policy while fixing any mean-field state. In practice, however, the policy and the mean-field state evolve simultaneously, as each agent is learning while playing. To bridge such a gap, we propose a fictitious play algorithm, which alternatively updates the policy (learning) and the mean-field state (playing) by one step of policy optimization and gradient descent, respectively. Despite the nonstationarity induced by such an alternating scheme, we prove that the proposed algorithm converges to the Nash equilibrium with an explicit convergence rate. To the best of our knowledge, it is the first provably efficient algorithm that achieves learning while playing via alternating updates.

Designing off-policy reinforcement learning algorithms is typically a very challenging task, because a desirable iteration update often involves an expectation over an on-policy distribution. Prior off-policy actor-critic (AC) algorithms have introduced a new critic that uses the density ratio for adjusting the distribution mismatch in order to stabilize the convergence, but at the cost of potentially introducing high biases due to the estimation errors of both the density ratio and value function. In this paper, we develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP, which can take advantage of learned nuisance functions to reduce estimation errors. Moreover, DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize, and is thus more sample efficient than prior algorithms that adopt either two timescale or nested-loop structure. We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $\epsilon$-accurate optimal policy. We also show that the overall convergence of DR-Off-PAC is doubly robust to the approximation errors that depend only on the expressive power of approximation functions. To the best of our knowledge, our study establishes the first overall sample complexity analysis for single time-scale off-policy AC algorithm.

Exploration methods based on pseudo-count of transitions or curiosity of dynamics have achieved promising results in solving reinforcement learning with sparse rewards. However, such methods are usually sensitive to environmental dynamics-irrelevant information, e.g., white-noise. To handle such dynamics-irrelevant information, we propose a Dynamic Bottleneck (DB) model, which attains a dynamics-relevant representation based on the information-bottleneck principle. Based on the DB model, we further propose DB-bonus, which encourages the agent to explore state-action pairs with high information gain. We establish theoretical connections between the proposed DB-bonus, the upper confidence bound (UCB) for linear case, and the visiting count for tabular case. We evaluate the proposed method on Atari suits with dynamics-irrelevant noises. Our experiments show that exploration with DB bonus outperforms several state-of-the-art exploration methods in noisy environments.

Mean-Field Multi-Agent Reinforcement Learning (MF-MARL) is attractive in the applications involving a large population of homogeneous agents, as it exploits the permutation invariance of agents and avoids the curse of many agents. Most existing results only focus on online settings, in which agents can interact with the environment during training. In some applications such as social welfare optimization, however, the interaction during training can be prohibitive or even unethical in the societal systems. To bridge such a gap, we propose a SAFARI (peSsimistic meAn-Field vAlue iteRatIon) algorithm for off-line MF-MARL, which only requires a handful of pre-collected experience data. Theoretically, under a weak coverage assumption that the experience dataset contains enough information about the optimal policy, we prove that for an episodic mean-field MDP with a horizon $H$ and $N$ training trajectories, SAFARI attains a sub-optimality gap of $\mathcal{O}(H^2d_{\rm eff} /\sqrt{N})$, where $d_{\rm eff}$ is the effective dimension of the function class for parameterizing the value function, but independent on the number of agents. Numerical experiments are provided.

We study risk-sensitive reinforcement learning (RL) based on the entropic risk measure. Although existing works have established non-asymptotic regret guarantees for this problem, they leave open an exponential gap between the upper and lower bounds. We identify the deficiencies in existing algorithms and their analysis that result in such a gap. To remedy these deficiencies, we investigate a simple transformation of the risk-sensitive Bellman equations, which we call the exponential Bellman equation. The exponential Bellman equation inspires us to develop a novel analysis of Bellman backup procedures in risk-sensitive RL algorithms, and further motivates the design of a novel exploration mechanism. We show that these analytic and algorithmic innovations together lead to improved regret upper bounds over existing ones.

This paper proposes a new algorithm -- the \underline{S}ingle-timescale Do\underline{u}ble-momentum \underline{St}ochastic \underline{A}pprox\underline{i}matio\underline{n} (SUSTAIN) -- for tackling stochastic unconstrained bilevel optimization problems. We focus on bilevel problems where the lower level subproblem is strongly-convex and the upper level objective function is smooth. Unlike prior works which rely on \emph{two-timescale} or \emph{double loop} techniques, we design a stochastic momentum-assisted gradient estimator for both the upper and lower level updates. The latter allows us to control the error in the stochastic gradient updates due to inaccurate solution to both subproblems. If the upper objective function is smooth but possibly non-convex, we show that {SUSTAIN}~requires $O(\epsilon^{-3/2})$ iterations (each using $O(1)$ samples) to find an $\epsilon$-stationary solution. The $\epsilon$-stationary solution is defined as the point whose squared norm of the gradient of the outer function is less than or equal to $\epsilon$. The total number of stochastic gradient samples required for the upper and lower level objective functions matches the best-known complexity for single-level stochastic gradient algorithms. We also analyze the case when the upper level objective function is strongly-convex.

Despite the tremendous success of reinforcement learning (RL) with function approximation, efficient exploration remains a significant challenge, both practically and theoretically. In particular, existing theoretically grounded RL algorithms based on upper confidence bounds (UCBs), such as optimistic least-squares value iteration (LSVI), are often incompatible with practically powerful function approximators, such as neural networks. In this paper, we develop a variant of \underline{boo}tstrapped LS\underline{VI}, namely BooVI, which bridges such a gap between practice and theory. Practically, BooVI drives exploration through (re)sampling, making it compatible with general function approximators. Theoretically, BooVI inherits the worst-case $\tilde{O}(\sqrt{d^3 H^3 T})$-regret of optimistic LSVI in the episodic linear setting. Here $d$ is the feature dimension, $H$ is the episode horizon, and $T$ is the total number of steps.

Empowered by neural networks, deep reinforcement learning (DRL) achieves tremendous empirical success. However, DRL requires a large dataset by interacting with the environment, which is unrealistic in critical scenarios such as autonomous driving and personalized medicine. In this paper, we study how to incorporate the dataset collected in the offline setting to improve the sample efficiency in the online setting. To incorporate the observational data, we face two challenges. (a) The behavior policy that generates the observational data may depend on unobserved random variables (confounders), which affect the received rewards and transition dynamics. (b) Exploration in the online setting requires quantifying the uncertainty given both the observational and interventional data. To tackle such challenges, we propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner. DOVI explicitly adjusts for the confounding bias in the observational data, where the confounders are partially observed or unobserved. In both cases, such adjustments allow us to construct the bonus based on a notion of information gain, which takes into account the amount of information acquired from the offline setting. In particular, we prove that the regret of DOVI is smaller than the optimal regret achievable in the pure online setting when the confounded observational data are informative upon the adjustments.

In constrained multi-objective RL, the goal is to learn a policy that achieves the best performance specified by a multi-objective preference function under a constraint. We focus on the offline setting where the RL agent aims to learn the optimal policy from a given dataset. This scenario is common in real-world applications where interactions with the environment are expensive and the constraint violation is dangerous. For such a setting, we transform the original constrained problem into a primal-dual formulation, which is solved via dual gradient ascent. Moreover, we propose to combine such an approach with pessimism to overcome the uncertainty in offline data, which leads to our Pessimistic Dual Iteration (PEDI). We establish upper bounds on both the suboptimality and constraint violation for the policy learned by PEDI based on an arbitrary dataset, which proves that PEDI is provably sample efficient. We also specialize PEDI to the setting with linear function approximation. To the best of our knowledge, we propose the first provably efficient constrained multi-objective RL algorithm with offline data without any assumption on the coverage of the dataset.

Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. However, most of the existing theoretical support for AC algorithms focuses on the case of linear function approximations, or linearized neural networks, where the feature representation is fixed throughout training. Such a limitation fails to capture the key aspect of representation learning in neural AC, which is pivotal in practical problems. In this work, we take a mean-field perspective on the evolution and convergence of feature-based neural AC. Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates. The critic is updated by temporal-difference (TD) learning with a larger stepsize while the actor is updated via proximal policy optimization (PPO) with a smaller stepsize. In the continuous-time and infinite-width limiting regime, when the timescales are properly separated, we prove that neural AC finds the globally optimal policy at a sublinear rate. Additionally, we prove that the feature representation induced by the critic network is allowed to evolve within a neighborhood of the initial one.

Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where \emph{function approximation} must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational and statistical efficiency, especially given the need to manage the exploration/exploitation tradeoff. As a result, a core RL question remains open: how can we design provably efficient RL algorithms that incorporate function approximation? This question persists even in a basic setting with linear dynamics and linear rewards, for which only linear function approximation is needed. This paper presents the first provable RL algorithm with both polynomial runtime and polynomial sample complexity in this linear setting, without requiring a “simulator” or additional assumptions. Concretely, we prove that an optimistic modification of Least-Squares Value Iteration (LSVI)—a classical algorithm frequently studied in the linear setting—achieves $\tilde{\mathcal{O}}(\sqrt{d^3H^3T})$ regret, where $d$ is the ambient dimension of feature space, $H$ is the length of each episode, and $T$ is the total number of steps. Importantly, such regret is independent of the number of states and actions.

In this work, we develop provably efficient reinforcement learning algorithms for two-player zero-sum Markov games with simultaneous moves. We consider a family of Markov games where the reward function and transition kernel possess a linear structure. Two settings are studied: In the offline setting, we control both players and the goal is to find the Nash Equilibrium efficiently by minimizing the worst-case duality gap. In the online setting, we control a single player and play against an arbitrary opponent; the goal is to minimize the regret. For both settings, we propose an optimistic variant of the least-squares minimax value iteration algorithm. We show that our algorithm is computationally efficient and provably achieves an $\tilde O(\sqrt{d^3 H^3 T} )$ upper bound on the duality gap and regret, without requiring additional assumptions on the sampling model. We highlight that our setting requires overcoming several new challenges that are absent in MDPs or turn-based Markov games. In particular, to achieve optimism under the simultaneous-move games, we construct both upper and lower confidence bounds of the value function, and then derive the optimistic policy by solving a general-sum matrix game with these bounds as the payoff matrices. As finding the Nash Equilibrium of this general-sum game is computationally hard, our algorithm instead solves for a Coarse Correlated Equilibrium (CCE), which can be obtained efficiently via linear programming. To our best knowledge, such a CCE-based mechanism for implementing optimism has not appeared in the literature and might be of interest in its own right.

While policy-based reinforcement learning (RL) achieves tremendous successes in practice, it is significantly less understood in theory, especially compared with value-based RL. In particular, it remains elusive how to design a provably efficient policy optimization algorithm that incorporates exploration. To bridge such a gap, this paper proposes an Optimistic variant of the Proximal Policy Optimization algorithm (OPPO), which follows an “optimistic version” of the policy gradient direction. This paper proves that, in the problem of episodic Markov decision process with linear function approximation, unknown transition, and adversarial reward with full-information feedback, OPPO achieves $\tilde{O}(\sqrt{d^2 H^3 T})$ regret. Here $d$ is the feature dimension, $H$ is the episode horizon, and $T$ is the total number of steps. To the best of our knowledge, OPPO is the first provably efficient policy optimization algorithm that explores.

We study the computational and statistical tradeoffs in inferring combinatorial structures of high dimensional simple zero-field ferromagnetic Ising model. Under the framework of oracle computational model where an algorithm interacts with an oracle that discourses a randomized version of truth, we characterize the computational lower bounds of learning combinatorial structures in polynomial time, under which no algorithms within polynomial-time can distinguish between graphs with and without certain structures. This hardness of learning with limited computational budget is shown to be characterized by a novel quantity called vertex overlap ratio. Such quantity is universally valid for many specific graph structures including cliques and nearest neighbors. On the other side, we attain the optimal rates for testing these structures against empty graph by proposing the quadratic testing statistics to match the lower bounds. We also investigate the relationship between computational bounds and information-theoretic bounds for such problems, and found gaps between the two boundaries in inferring some particular structures, especially for those with dense edges.

Graph representation learning is a ubiquitous task in machine learning where the goal is to embed each vertex into a low-dimensional vector space. We consider the bipartite graph and formalize its representation learning problem as a statistical estimation problem of parameters in a semiparametric exponential family distribution: the bipartite graph is assumed to be generated by a semiparametric exponential family distribution, whose parametric component is given by the proximity of outputs of two one-layer neural networks that take high-dimensional features as inputs, while nonparametric (nuisance) component is the base measure. In this setting, the representation learning problem is equivalent to recovering the weight matrices, and the main challenges of estimation arise from the nonlinearity of activation functions and the nonparametric nuisance component of the distribution. To overcome these challenges, we propose a pseudo-likelihood objective based on the rank-order decomposition technique and show that the proposed objective is strongly convex in a neighborhood around the ground truth, so that a gradient descent-based method achieves linear convergence rate. Moreover, we prove that the sample complexity of the problem is linear in dimensions (up to logarithmic factors), which is consistent with parametric Gaussian models. However, our estimator is robust to any model misspecification within the exponential family, which is validated in extensive experiments.

Deep reinforcement learning (RL) has achieved great empirical successes in various domains. However, the large search space of neural networks requires a large amount of data, which makes the current RL algorithms not sample efficient. Motivated by the fact that many environments with continuous state space have smooth transitions, we propose to learn a smooth policy that behaves smoothly with respect to states. We develop a new framework — \textbf{S}mooth \textbf{R}egularized \textbf{R}einforcement \textbf{L}earning ($\textbf{SR}^2\textbf{L}$), where the policy is trained with smoothness-inducing regularization. Such regularization effectively constrains the search space, and enforces smoothness in the learned policy. Moreover, our proposed framework can also improve the robustness of policy against measurement error in the state space, and can be naturally extended to distribubutionally robust setting. We apply the proposed framework to both on-policy (TRPO) and off-policy algorithm (DDPG). Through extensive experiments, we demonstrate that our method achieves improved sample efficiency and robustness.

Model-agnostic meta-learning (MAML) formulates meta-learning as a bilevel optimization problem, where the inner level solves each subtask based on a shared prior, while the outer level searches for the optimal shared prior by optimizing its aggregated performance over all the subtasks. Despite its empirical success, MAML remains less understood in theory, especially in terms of its global optimality, due to the nonconvexity of the meta-objective (the outer-level objective). To bridge such a gap between theory and practice, we characterize the optimality gap of the stationary points attained by MAML for both reinforcement learning and supervised learning, where the inner-level and outer-level problems are solved via first-order optimization methods. In particular, our characterization connects the optimality gap of such stationary points with (i) the functional geometry of inner-level objectives and (ii) the representation power of function approximators, including linear models and neural networks. To the best of our knowledge, our analysis establishes the global optimality of MAML with nonconvex meta-objectives for the first time.

Multi-agent reinforcement learning (MARL) achieves significant empirical successes. However, MARL suffers from the curse of many agents. In this paper, we exploit the symmetry of agents in MARL. In the most generic form, we study a mean-field MARL problem. Such a mean-field MARL is defined on mean-field states, which are distributions that are supported on continuous space. Based on the mean embedding of the distributions, we propose MF-FQI algorithm, which solves the mean-field MARL and establishes a non-asymptotic analysis for MF-FQI algorithm. We highlight that MF-FQI algorithm enjoys a “blessing of many agents” property in the sense that a larger number of observed agents improves the performance of MF-FQI algorithm.

Generative adversarial imitation learning (GAIL) demonstrates tremendous success in practice, especially when combined with neural networks. Different from reinforcement learning, GAIL learns both policy and reward function from expert (human) demonstration. Despite its empirical success, it remains unclear whether GAIL with neural networks converges to the globally optimal solution. The major difficulty comes from the nonconvex-nonconcave minimax optimization structure. To bridge the gap between practice and theory, we analyze a gradient-based algorithm with alternating updates and establish its sublinear convergence to the globally optimal solution. To the best of our knowledge, our analysis establishes the global optimality and convergence rate of GAIL with neural networks for the first time.

We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels, where the goal is to optimize the total reward under the risk measure of exponential utility. We propose two provably efficient model-free algorithms, Risk-Sensitive Value Iteration (RSVI) and Risk-Sensitive Q-learning (RSQ). These algorithms implement a form of risk-sensitive optimism in the face of uncertainty, which adapts to both risk-seeking and risk-averse modes of exploration. We prove that RSVI attains an \ensuremath{\tilde{O}\big(\lambda(|\beta| H^2) \cdot \sqrt{H^{3} S^{2}AT} \big)}$ regret, while RSQ attains an $\ensuremath{\tilde{O}\big(\lambda(|\beta| H^2) \cdot \sqrt{H^{4} SAT} \big)}$ regret, where $\lambda(u) = (e^{3u}-1)/u$ for $u>0$. In the above, $\beta$ is the risk parameter of the exponential utility function, $S$ the number of states, $A$ the number of actions, $T$ the total number of timesteps, and $H$ the episode length. On the flip side, we establish a regret lower bound showing that the exponential dependence on $|\beta|$ and $H$ is unavoidable for any algorithm with an $\tilde{O}(\sqrt{T})$ regret (even when the risk objective is on the same scale as the original reward), thus certifying the near-optimality of the proposed algorithms. Our results demonstrate that incorporating risk awareness into reinforcement learning necessitates an exponential cost in $|\beta|$ and $H$, which quantifies the fundamental tradeoff between risk sensitivity (related to aleatoric uncertainty) and sample efficiency (related to epistemic uncertainty). To the best of our knowledge, this is the first regret analysis of risk-sensitive reinforcement learning with the exponential utility.

We consider reinforcement learning (RL) in episodic MDPs with adversarial full-information reward feedback and unknown fixed transition kernels. We propose two model-free policy optimization algorithms, POWER and POWER++, and establish guarantees for their dynamic regret. Compared with the classical notion of static regret, dynamic regret is a stronger notion as it explicitly accounts for the non-stationarity of environments. The dynamic regret attained by the proposed algorithms interpolates between different regimes of non-stationarity, and moreover satisfies a notion of adaptive (near-)optimality, in the sense that it matches the (near-)optimal static regret under slow-changing environments. The dynamic regret bound features two components, one arising from exploration, which deals with the uncertainty of transition kernels, and the other arising from adaptation, which deals with non-stationary environments. Specifically, we show that POWER++ improves over POWER on the second component of the dynamic regret by actively adapting to non-stationarity through prediction. To the best of our knowledge, our work is the first dynamic regret analysis of model-free RL algorithms in non-stationary environments.

This paper develops a Pontryagin differentiable programming (PDP) methodology, which establishes a unified framework to solve a broad class of learning and control tasks. The PDP distinguishes from existing methods by two novel techniques: first, we differentiate through Pontryagin's Maximum Principle, and this allows to obtain the analytical derivative of a trajectory with respect to tunable parameters within an optimal control system, enabling end-to-end learning of dynamics, policies, or/and control objective functions; and second, we propose an auxiliary control system in the backward pass of the PDP framework, and the output of this auxiliary control system is the analytical derivative of the original system's trajectory with respect to the parameters, which can be iteratively solved using standard control tools. We investigate three learning modes of the PDP: inverse reinforcement learning, system identification, and control/planning. We demonstrate the capability of the PDP in each learning mode on different high-dimensional systems, including multilink robot arm, 6-DoF maneuvering UAV, and 6-DoF rocket powered landing.

In a social system, the self-interest of agents can be detrimental to the collective good, sometimes leading to social dilemmas. To resolve such a conflict, a central designer may intervene by either redesigning the system or incentivizing the agents to change their behaviors. To be effective, the designer must anticipate how the agents react to the intervention, which is dictated by their often unknown payoff functions. Therefore, learning about the agents is a prerequisite for intervention. In this paper, we provide a unified framework for learning and intervention in games. We cast the equilibria of games as individual layers and integrate them into an end-to-end optimization framework. To enable the backward propagation through the equilibria of games, we propose two approaches, respectively based on explicit and implicit differentiation. Specifically, we cast the equilibria as the solutions to variational inequalities (VIs). The explicit approach unrolls the projection method for solving VIs, while the implicit approach exploits the sensitivity of the solutions to VIs. At the core of both approaches is the differentiation through a projection operator. Moreover, we establish the correctness of both approaches and identify the conditions under which one approach is more desirable than the other. The analytical results are validated using several real-world problems.

Structural equation models (SEMs) are widely used in sciences, ranging from economics to psychology, to uncover causal relationships underlying a complex system under consideration and estimate structural parameters of interest. We study estimation in a class of generalized SEMs where the object of interest is defined as the solution to a linear operator equation. We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using the stochastic gradient descent. We consider both 2-layer and multi-layer NNs with ReLU activation functions and prove global convergence in an overparametrized regime, where the number of neurons is diverging. The results are established using techniques from online learning and local linearization of NNs, and improve in several aspects the current state-of-the-art. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.

We consider online learning for episodic stochastically constrained Markov decision processes (CMDP), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the episodes, whereas both the loss received and the budget consumption are revealed at the end of each episode. Previous works solve this problem under the restrictive assumption that the transition model of the MDP is known a priori and establish regret bounds that depend polynomially on the cardinalities of the state space $\mathcal{S}$ and the action space $\mathcal{A}$. In this work, we propose a new \emph{upper confidence primal-dual} algorithm, which only requires the trajectories sampled from the transition model. In particular, we prove that the proposed algorithm achieves $\widetilde{\mathcal{O}}(L|\mathcal{S}|\sqrt{|\mathcal{A}|T})$ upper bounds of both the regret and the constraint violation, where $L$ is the length of each episode. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning, which demonstrates the power of ``optimism in the face of uncertainty'' in constrained online learning.

This paper studies a gradient temporal difference (GTD) algorithm using neural network (NN) function approximators to minimize the mean squared Bellman error (MSBE). For off-policy learning, we show that the minimum MSBE problem can be recast into a min-max optimization involving a pair of over-parameterized primal-dual NNs. The resultant formulation can then be tackled using a neural GTD algorithm. We analyze the convergence of the proposed algorithm with a 2-layer ReLU NN architecture using $m$ neurons and prove that it computes an approximate optimal solution to the minimum MSBE problem as $m \rightarrow \infty$.

Reinforcement learning (RL) algorithms combined with modern function approximators such as kernel functions and deep neural networks have achieved significant empirical successes in large-scale application problems with a massive number of states. From a theoretical perspective, however, RL with functional approximation poses a fundamental challenge to developing algorithms with provable computational and statistical efficiency, due to the need to take into consideration both the exploration-exploitation tradeoff that is inherent in RL and the bias-variance tradeoff that is innate in statistical estimation. To address such a challenge, focusing on the episodic setting where the action-value functions are represented by a kernel function or over-parametrized neural network, we propose the first provable RL algorithm with both polynomial runtime and sample complexity, without additional assumptions on the data-generating model. In particular, for both the kernel and neural settings, we prove that an optimistic modification of the least-squares value iteration algorithm incurs an $\tilde{\mathcal{O}}(\delta_{\cF} H^2 \sqrt{T})$ regret, where $\delta_{\cF}$ characterizes the intrinsic complexity of the function class $\cF$, $H$ is the length of each episode, and $T$ is the total number of episodes. Our regret bounds are independent of the number of states and therefore even allows it to diverge, which exhibits the benefit of function approximation.

Temporal-difference and Q-learning play a key role in deep reinforcement learning, where they are empowered by expressive nonlinear function approximators such as neural networks. At the core of their empirical successes is the learned feature representation, which embeds rich observations, e.g., images and texts, into the latent space that encodes semantic structures. Meanwhile, the evolution of such a feature representation is crucial to the convergence of temporal-difference and Q-learning. In particular, temporal-difference learning converges when the function approximator is linear in a feature representation, which is fixed throughout learning, and possibly diverges otherwise. We aim to answer the following questions: When the function approximator is a neural network, how does the associated feature representation evolve? If it converges, does it converge to the optimal one? We prove that utilizing an overparameterized two-layer neural network, temporal-difference and Q-learning globally minimize the mean-squared projected Bellman error at a sublinear rate. Moreover, the associated feature representation converges to the optimal one, generalizing the previous analysis of Cai et al. (2019) in the neural tangent kernel regime, where the associated feature representation stabilizes at the initial one. The key to our analysis is a mean-field perspective, which connects the evolution of a finite-dimensional parameter to its limiting counterpart over an infinite-dimensional Wasserstein space. Our analysis generalizes to soft Q-learning, which is further connected to policy gradient.

The goal of noisy high-dimensional phase retrieval is to estimate an $s$-sparse parameter $\boldsymbol{\beta}^*\in \mathbb{R}^d$ from $n$ realizations of the model $Y = (\mathbf{X}^T \boldsymbol{\beta}^*)^2 + \varepsilon$. Based on this model, we propose a significant semi-parametric generalization called misspecified phase retrieval (MPR), in which $Y = f(\mathbf{X}^T \boldsymbol{\beta}^*, \varepsilon)$ with unknown $f$ and $\operatorname{Cov}(Y, (\mathbf{X}^T \boldsymbol{\beta}^*)^2) > 0$. For example, MPR encompasses $Y = h(|\mathbf{X}^T \boldsymbol{\beta}^*|) + \varepsilon$ with increasing $h$ as a special case. Despite the generality of the MPR model, it eludes the reach of most existing semi-parametric estimators. In this paper, we propose an estimation procedure, which consists of solving a cascade of two convex programs and provably recovers the direction of $\boldsymbol{\beta}^*$. Furthermore, we prove that our procedure is minimax optimal over the class of MPR models. Interestingly, our minimax analysis characterizes the statistical price of misspecifying the link function in phase retrieval models. Our theory is backed up by thorough numerical results.

We consider the estimation and inference of graphical models that characterize the dependency structure of high-dimensional tensor-valued data. To facilitate the estimation of the precision matrix corresponding to each way of the tensor, we assume the data follow a tensor normal distribution whose covariance has a Kronecker product structure. A critical challenge in the estimation and inference of this model is the fact that its penalized maximum likelihood estimation involves minimizing a non-convex objective function. To address it, this paper makes two contributions: (i) In spite of the non-convexity of this estimation problem, we prove that an alternating minimization algorithm, which iteratively estimates each sparse precision matrix while fixing the others, attains an estimator with an optimal statistical rate of convergence. (ii) We propose a de-biased statistical inference procedure for testing hypotheses on the true support of the sparse precision matrices, and employ it for testing a growing number of hypothesis with false discovery rate (FDR) control. The asymptotic normality of our test statistic and the consistency of FDR control procedure are established. Our theoretical results are backed up by thorough numerical studies and our real applications on neuroimaging studies of Autism spectrum disorder and users' advertising click analysis bring new scientific findings and business insights. The proposed methods are encoded into a publicly available R package Tlasso.

We consider estimating a high-dimensional vector from non-linear measurements where the unknown vector is represented by a generative model $G:\mathbb{R}^k\rightarrow\mathbb{R}^d$ with $k\ll d$. Such a model poses structural priors on the unknown vector without having a dedicated basis, and in particular allows new and efficient approaches solving recovery problems with number of measurements far less than the ambient dimension of the vector. While progresses have been made recently regarding theoretical understandings on the linear Gaussian measurements, much less is known when the model is possibly misspecified and the measurements are non-Gaussian. In this paper, we make a step towards such a direction by considering the scenario where the measurements are non-Gaussian, subject to possibly unknown nonlinear transformations and the responses are heavy-tailed. We then propose new estimators via score functions based on the first and second order Stein’s identity, and prove the sample size bound of $m=\mathcal{O}(k\varepsilon^{-2}\log(L/\varepsilon))$ achieving an $\varepsilon$ error in the form of exponential concentration inequalities. Furthermore, for the special case of multi-layer ReLU generative model, we improve the sample bound by a logarithm factor to $m=\mathcal{O}(k\varepsilon^{-2}\log(d))$, matching the state-of-art statistical rate in compressed sensing for estimating $k$-sparse vectors. On the technical side, we develop new chaining methods bounding heavy-tailed processes, which could be of independent interest.

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence of neural TD remains unclear. In this paper, we prove for the first time that neural TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation. In particular, we show how such global convergence is enabled by the overparametrization of neural networks, which also plays a vital role in the empirical success of neural TD. Beyond policy evaluation, we establish the global convergence of neural (soft) Q-learning, which is further connected to that of policy gradient algorithms.

Proximal policy optimization and trust region policy optimization (PPO and TRPO) with actor and critic parametrized by neural networks achieve significant empirical success in deep reinforcement learning. However, due to nonconvexity, the global convergence of PPO and TRPO remains less understood, which separates theory from practice. In this paper, we prove that a variant of PPO and TRPO equipped with overparametrized neural networks converges to the globally optimal policy at a sublinear rate. The key to our analysis is the global convergence of infinite-dimensional mirror descent under a notion of one-point monotonicity, where the gradient and iterate are instantiated by neural networks. In particular, the desirable representation power and optimization geometry induced by the overparametrization of such neural networks allow them to accurately approximate the infinite-dimensional gradient and iterate.

Policy evaluation with smooth and nonlinear function approximation has shown great potential for reinforcement learning. Compared to linear function approxi- mation, it allows for using a richer class of approximation functions such as the neural networks. Traditional algorithms are based on two timescales stochastic approximation whose convergence rate is often slow. This paper focuses on an offline setting where a trajectory of $m$ state-action pairs are observed. We formulate the policy evaluation problem as a non-convex primal-dual, finite-sum optimization problem, whose primal sub-problem is non-convex and dual sub-problem is strongly concave. We suggest a single-timescale primal-dual gradient algorithm with variance reduction, and show that it converges to an $\epsilon$-stationary point using $O(m/\epsilon)$ calls (in expectation) to a gradient oracle.

We study the statistical-computational tradeoffs in a high dimensional single index model $Y=f(X^\top\beta^*) +\epsilon$, where $f$ is unknown, $X$ is a Gaussian vector and $\beta^*$ is $s$-sparse with unit norm. When $\cov(Y,X^\top\beta^*)\neq 0$, \cite{plan2016generalized} shows that the direction and support of $\beta^*$ can be recovered using a generalized version of Lasso. In this paper, we investigate the case when this critical assumption fails to hold, where the problem becomes considerably harder. Using the statistical query model to characterize the computational cost of an algorithm, we show that when $\cov(Y,X^\top\beta^*)=0$ and $\cov(Y,(X^\top\beta^*)^2)>0$, no computationally tractable algorithms can achieve the information-theoretic limit of the minimax risk. This implies that one must pay an extra computational cost for the nonlinearity involved in the model.

Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence is known to be fragile. To understand the instability of actor-critic, we focus on its application to linear quadratic regulators, a simple yet fundamental setting of reinforcement learning. We establish a nonasymptotic convergence analysis of actor- critic in this setting. In particular, we prove that actor-critic finds a globally optimal pair of actor (policy) and critic (action-value function) at a linear rate of convergence. Our analysis may serve as a preliminary step towards a complete theoretical understanding of bilevel optimization with nonconvex subproblems, which is NP-hard in the worst case and is often solved using heuristics.

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For such a problem, we construct a sequence of surrogate convex constrained optimization problems by replacing the nonconvex functions locally with convex quadratic functions obtained from policy gradient estimators. We prove that the solutions to these surrogate problems converge to a stationary point of the original nonconvex problem. Furthermore, to extend our theoretical results, we apply our algorithm to examples of optimal control and multi-agent reinforcement learning with safety constraints.

We study the parameter estimation problem for a varying index coefficient model in high dimensions. Unlike the most existing works that iteratively estimate the parameters and link functions, based on the generalized Stein's identity, we propose computationally efficient estimators for the high-dimensional parameters without estimating the link functions. We consider two different setups where we either estimate each sparse parameter vector individually or estimate the parameters simultaneously as a sparse or low-rank matrix. For all these cases, our estimators are shown to achieve optimal statistical rates of convergence (up to logarithmic terms in the low-rank setting). Moreover, throughout our analysis, we only require the covariate to satisfy certain moment conditions, which is significantly weaker than the Gaussian or elliptically symmetric assumptions that are commonly made in the existing literature. Finally, we conduct extensive numerical experiments to corroborate the theoretical results.

We propose a general theory for studying the landscape of nonconvex optimization with underlying symmetric structures for a class of machine learning problems (e.g., low-rank matrix factorization, phase retrieval, and deep linear neural networks). In particular, we characterize the locations of stationary points and the null space of Hessian matrices of the objective function via the lens of invariant groups. As a major motivating example, we apply the proposed general theory to characterize the global landscape of the nonconvex optimization in low-rank matrix factorization problem. We illustrate how the rotational symmetry group gives rise to infinitely many nonisolated strict saddle points and equivalent global minima of the objective function. By explicitly identifying all stationary points, we divide the entire parameter space into three regions: (R1) the region containing the neighborhoods of all strict saddle points where the objective has negative curvature; (R2) the region containing neighborhoods of all global minima, where the objective enjoys strong convexity along certain directions; and (R3) the complement of the above regions, where the gradient has sufficiently large magnitude. We further extend our result to the matrix sensing problem. Such global landscape implies that strong global convergence guarantees for popular iterative algorithms with arbitrary initial solutions.

This paper proposes a distributed privacy-preserving sparse PCA (DPS-PCA) algorithm that generates a minimax-optimal sparse PCA estimator under differential privacy constraints. In a distributed optimization framework, data providers can use this algorithm to collaboratively analyze the union of their data sets while limiting the disclosure of their private information. DPS-PCA can recover the leading eigenspace of the population covariance at a geometric convergence rate, and simultaneously achieves the optimal minimax statistical error for high-dimensional data. Our algorithm provides fine-tuned control over the tradeoff between estimation accuracy and privacy preservation. Numerical simulations demonstrate that DPS-PCA significantly outperforms other privacy-preserving PCA methods in terms of estimation accuracy and computational efficiency.

We study the high-dimensional signal estimation problem with nonlinear measurements, where the signal of interest is either sparse or low-rank. In both settings, our estimator is formulated as the minimizer of the nonlinear least-squares loss function under a combinatorial constraint, which is obtained efficiently by the iterative hard thresholding (IHT) algorithm. Although the loss function is non-convex due to the nonlinearity of the statistical model, the IHT algorithm is shown to converge linearly to a point with optimal statistical accuracy using arbitrary initialization. Moreover, our analysis only hinges on conditions similar to those required in the linear case. Detailed numerical experiments are included to corroborate the theoretical results.

Truth discovery aims at obtaining the most credible information from multiple sources that provide noisy and conflicting values. Due to the ubiquitous existence of data conflict in practice, truth discovery has been attracting a lot of research attention recently. Unfortunately, existing truth discovery models all miss an important issue of truth discovery - the truth evolution problem. In many real-life scenarios, the latent true value often keeps changing dynamically over time instead of staying static. We study the dynamic truth discovery problem in the space of numerical truth discovery. This problem cannot be addressed by existing models because of the new challenges of capturing time-evolving source dependency in a continuous space as well as handling missing data on the fly. We propose a model named EvolvT for dynamic truth discovery on numerical data. With the hidden Markov framework, EvolvT captures three key aspects of dynamic truth discovery with a unified model: truth transition regularity, source quality, and source dependency. The most distinguishable feature of the modeling part of EvolvT is that it employs Kalman filtering to model truth evolution. As such, EvolvT not only can principally infer source dependency in a continuous space, but also can handle missing data in a natural way. We establish an expectation-maximization (EM) algorithm for parameter inference of EvolvT and present an efficient online version for the parameter inference procedure. Our experiments on real-world applications demonstrate its advantages over the state-of-the-art truth discovery approaches.

We study the hypothesis testing problem of inferring the existence of combinatorial structures in undirected graphical models. Although there exist extensive studies on the information-theoretic limits of this problem, it remains largely unexplored whether such limits can be attained by efficient algorithms. In this paper, we quantify the minimum computational complexity required to attain the information-theoretic limits based on an oracle computational model. We prove that, for testing common combinatorial structures, such as clique, nearest neighbor graph and perfect matching, against an empty graph, or large clique against small clique, the information-theoretic limits are provably unachievable by tractable algorithms in general. More importantly, we define structural quantities called the weak and strong edge densities, which offer deep insight into the existence of such computational-statistical tradeoffs. To the best of our knowledge, our characterization is the first to identify and explain the fundamental tradeoffs between statistics and computation for combinatorial inference problems in undirected graphical models.

Learning from pairwise measurements naturally arises from many applications, such as rank aggregation, ordinal embedding, and crowdsourcing. However, most existing models and algorithms are susceptible to potential model misspecification. In this paper, we study a semiparametric model where the pairwise measurements follow a natural exponential family distribution with an unknown base measure. Such a semiparametric model includes various popular parametric models, such as the Bradley-Terry-Luce model and the paired cardinal model, as special cases. To estimate this semiparametric model without specifying the base measure, we propose a data augmentation technique to create virtual examples, which enables us to define a contrastive estimator. In particular, we prove that such a contrastive estimator is invariant to model misspecification within the natural exponential family, and moreover, attains the optimal statistical rate of convergence up to a logarithmic factor. We provide numerical experiments to corroborate our theory.

Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jointly observed state-action pairs and private local rewards collaborate to learn the value of a given policy. In this paper, we propose a double averaging scheme, where each agent iteratively performs averaging over both space and time to incorporate neighboring gradient information and local reward information, respectively. We prove that the proposed algorithm converges to the optimal solution at a global geometric rate. In particular, such an algorithm is built upon a primal-dual reformulation of the mean squared Bellman error minimization problem, which gives rise to a decentralized convex-concave saddle-point problem. To the best of our knowledge, the proposed double averaging primal-dual optimization algorithm is the first to achieve fast finite-time convergence on decentralized convex-concave saddle-point problems.

The success of machine learning methods heavily relies on having an appropriate representation for data at hand. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about data. However, recently there has been a surge in approaches that learn how to encode the data automatically in a low dimensional space. Exponential family embedding provides a probabilistic framework for learning low-dimensional representation for various types of high-dimensional data. Though successful in practice, theoretical underpinnings for exponential family embeddings have not been established. In this paper, we study the Gaussian embedding model and develop the first theoretical results for exponential family embedding models. First, we show that, under a mild condition, the embedding structure can be learned from one observation by leveraging the parameter sharing between different contexts even though the data are dependent with each other. Second, we study properties of two algorithms used for learning the embedding structure and establish convergence results for each of them. The first algorithm is based on a convex relaxation, while the other solved the non-convex formulation of the problem directly. Experiments demonstrate the effectiveness of our approach.

We consider estimating the parametric components of semiparametric multi-index models in high dimensions. To bypass the requirements of Gaussianity or elliptical symmetry of covariates in existing methods, we propose to leverage a second-order Stein’s method with score function-based corrections. We prove that our estimator achieves a near-optimal statistical rate of convergence even when the score function or the response variable is heavy-tailed. To establish the key concentration results, we develop a data-driven truncation argument that may be of independent interest. We supplement our theoretical findings with simulations.

In this paper, we present a nonconvex alternating minimization optimization algorithm for low-rank and sparse structure pursuit. Compared with convex relaxation based methods, the proposed algorithm is computationally more efficient for large scale problems. In our study, we define a notion of bounded difference of gradients, based on which we rigorously prove that with suitable initialization, the proposed nonconvex optimization algorithm enjoys linear convergence to the global optima and exactly recovers the underlying low rank and sparse matrices under standard conditions such as incoherence and sparsity conditions. For a wide range of statistical models such as multi-task learning and robust principal component analysis (RPCA), our algorithm provides a principled approach to learning the low rank and sparse structures with provable guarantee. Thorough experiments on both synthetic and real datasets backup our theory.

Many high dimensional sparse learning problems are formulated as nonconvex optimization. A popular approach to solve these nonconvex optimization problems is through convex relaxations such as linear and semidefinite programming. In this paper, we study the statistical limits of convex relaxations. Particularly, we consider two problems: Mean estimation for sparse principal submatrix and edge probability estimation for stochastic block model. We exploit the sum-of-squares relaxation hierarchy to sharply characterize the limits of a broad class of convex relaxations. Our result shows statistical optimality needs to be compromised for achieving computational tractability using convex relaxations. Compared with existing results on computational lower bounds for statistical problems, which consider general polynomial-time algorithms and rely on computational hardness hypotheses on problems like planted clique detection, our theory focuses on a broad class of convex relaxations and does not rely on unproven hypotheses.

We study parameter estimation for sparse nonlinear regression. More specifically, we assume the data are given by y = f( \bf x^T \bf β^* ) + ε, where f is nonlinear. To recover \bf βs, we propose an \ell_1-regularized least-squares estimator. Unlike classical linear regression, the corresponding optimization problem is nonconvex because of the nonlinearity of f. In spite of the nonconvexity, we prove that under mild conditions, every stationary point of the objective enjoys an optimal statistical rate of convergence. Detailed numerical results are provided to back up our theory.

In the information age, people can easily collect information about the same set of entities from multiple sources, among which conflicts are inevitable. This leads to an important task, truth discovery, i.e., to identify true facts (truths) via iteratively updating truths and source reliability. However, the convergence to the truths is never discussed in existing work, and thus there is no theoretical guarantee in the results of these truth discovery approaches. In contrast, in this paper we propose a truth discovery approach with theoretical guarantee. We propose a randomized gaussian mixture model (RGMM) to represent multi-source data, where truths are model parameters. We incorporate source bias which captures its reliability degree into RGMM formulation. The truth discovery task is then modeled as seeking the maximum likelihood estimate (MLE) of the truths. Based on expectation-maximization (EM) techniques, we propose population-based (i.e., on the limit of infinite data) and sample-based (i.e., on a finite set of samples) solutions for the MLE. Theoretically, we prove that both solutions are contractive to an ε-ball around the MLE, under certain conditions. Experimentally, we evaluate our method on both simulated and real-world datasets. Experimental results show that our method achieves high accuracy in identifying truths with convergence guarantee.

The importance of studying the robustness of learners to malicious data is well established. While much work has been done establishing both robust estimators and effective data injection attacks when the attacker is omniscient, the ability of an attacker to provably harm learning while having access to little information is largely unstudied. We study the potential of a “blind attacker” to provably limit a learner’s performance by data injection attack without observing the learner’s training set or any parameter of the distribution from which it is drawn. We provide examples of simple yet effective attacks in two settings: firstly, where an “informed learner” knows the strategy chosen by the attacker, and secondly, where a “blind learner” knows only the proportion of malicious data and some family to which the malicious distribution chosen by the attacker belongs. For each attack, we analyze minimax rates of convergence and establish lower bounds on the learner’s minimax risk, exhibiting limits on a learner’s ability to learn under data injection attack even when the attacker is “blind”.

We study a stochastic and distributed algorithm for nonconvex problems whose objective consists a sum $N$ nonconvex $L_i/N$-smooth functions, plus a nonsmooth regularizer. The proposed NonconvEx primal-dual SpliTTing (NESTT) algorithm splits the problem into $N$ subproblems, and utilizes an augmented Lagrangian based primal-dual scheme to solve it in a distributed and stochastic manner. With a special non-uniform sampling, a version of NESTT achieves $\epsilon$-stationary solution using $\mathcal{O}((\sum_{i=1}^N\sqrt{L_i/N})^2/\epsilon)$ gradient evaluations, which can be up to $\mathcal{O}(N)$ times better than the (proximal) gradient descent methods. It also achieves Q-linear convergence rate for nonconvex $\ell_1$ penalized quadratic problems with polyhedral constraints. Further, we reveal a fundamental connection between {\it primal-dual} based methods and a few {\it primal only} methods such as IAG/SAG/SAGA.

Solving statistical learning problems often involves nonconvex optimization. Despite the empirical success of nonconvex statistical optimization methods, their global dynamics, especially convergence to the desirable local minima, remain less well understood in theory. In this paper, we propose a new analytic paradigm based on diffusion processes to characterize the global dynamics of nonconvex statistical optimization. As a concrete example, we study stochastic gradient descent (SGD) for the tensor decomposition formulation of independent component analysis. In particular, we cast different phases of SGD into diffusion processes, i.e., solutions to stochastic differential equations. Initialized from an unstable equilibrium, the global dynamics of SGD transit over three consecutive phases: (i) an unstable Ornstein-Uhlenbeck process slowly departing from the initialization, (ii) the solution to an ordinary differential equation, which quickly evolves towards the desirable local minimum, and (iii) a stable Ornstein-Uhlenbeck process oscillating around the desirable local minimum. Our proof techniques are based upon Stroock and Varadhan’s weak convergence of Markov chains to diffusion processes, which are of independent interest.

The goal of noisy high-dimensional phase retrieval is to estimate an $s$-sparse parameter $\boldsymbol{\beta}^*\in \mathbb{R}^d$ from $n$ realizations of the model $Y = (\boldsymbol{X}^{\top} \boldsymbol{\beta}^*)^2 + \varepsilon$. Based on this model, we propose a significant semi-parametric generalization called misspecified phase retrieval (MPR), in which $Y = f(\boldsymbol{X}^{\top}\boldsymbol{\beta}^*, \varepsilon)$ with unknown $f$ and $\operatorname{Cov}(Y, (\boldsymbol{X}^{\top}\boldsymbol{\beta}^*)^2) > 0$. For example, MPR encompasses $Y = h(|\boldsymbol{X}^{\top} \boldsymbol{\beta}^*|) + \varepsilon$ with increasing $h$ as a special case. Despite the generality of the MPR model, it eludes the reach of most existing semi-parametric estimators. In this paper, we propose an estimation procedure, which consists of solving a cascade of two convex programs and provably recovers the direction of $\boldsymbol{\beta}^*$. Our theory is backed up by thorough numerical results.

We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1-\alpha$. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the statistical accuracies and computational efficiency of these algorithms depend on the degree of supervision, which is quantified by $\alpha$. In this paper, we characterize the effect of $\alpha$ by establishing the information-theoretic and computational boundaries, namely, the minimax-optimal statistical accuracy that can be achieved by all algorithms, and polynomial-time algorithms under an oracle computational model. For small $\alpha$, our result shows a gap between these two boundaries, which represents the computational price of achieving the information-theoretic boundary due to the lack of supervision. Interestingly, we also show that this gap narrows as $\alpha$ increases. In other words, having more supervision, i.e., more correct labels, not only improves the optimal statistical accuracy as expected, but also enhances the computational efficiency for achieving such accuracy.

We consider the estimation of sparse graphical models that characterize the dependency structure of high-dimensional tensor-valued data. To facilitate the estimation of the precision matrix corresponding to each way of the tensor, we assume the data follow a tensor normal distribution whose covariance has a Kronecker product structure. The penalized maximum likelihood estimation of this model involves minimizing a non-convex objective function. In spite of the non-convexity of this estimation problem, we prove that an alternating minimization algorithm, which iteratively estimates each sparse precision matrix while fixing the others, attains an estimator with the optimal statistical rate of convergence as well as consistent graph recovery. Notably, such an estimator achieves estimation consistency with only one tensor sample, which is unobserved in previous work. Our theoretical results are backed by thorough numerical studies.

We provide a general theory of the expectation-maximization (EM) algorithm for inferring high dimensional latent variable models. In particular, we make two contributions: (i) For parameter estimation, we propose a novel high dimensional EM algorithm which naturally incorporates sparsity structure into parameter estimation. With an appropriate initialization, this algorithm converges at a geometric rate and attains an estimator with the (near-)optimal statistical rate of convergence. (ii) Based on the obtained estimator, we propose a new inferential procedure for testing hypotheses for low dimensional components of high dimensional parameters. For a broad family of statistical models, our framework establishes the first computationally feasible approach for optimal estimation and asymptotic inference in high dimensions.

Linear regression studies the problem of estimating a model parameter $\beta^* \in \R^p$, from $n$ observations $\{(y_i,x_i)\}_{i=1}^n$ from linear model $y_i = \langle \x_i,\beta^* \rangle + \epsilon_i$. We consider a significant generalization in which the relationship between $\langle x_i,\beta^* \rangle$ and $y_i$ is noisy, quantized to a single bit, potentially nonlinear, noninvertible, as well as unknown. This model is known as the single-index model in statistics, and, among other things, it represents a significant generalization of one-bit compressed sensing. We propose a novel spectral-based estimation procedure and show that we can recover $\beta^*$ in settings (i.e., classes of link function $f$) where previous algorithms fail. In general, our algorithm requires only very mild restrictions on the (unknown) functional relationship between $y_i$ and $\langle x_i,\beta^* \rangle$. We also consider the high dimensional setting where $\beta^*$ is sparse, and introduce a two-stage nonconvex framework that addresses estimation challenges in high dimensional regimes where $p \gg n$. For a broad class of link functions between $\langle x_i,\beta^* \rangle$ and $y_i$, we establish minimax lower bounds that demonstrate the optimality of our estimators in both the classical and high dimensional regimes.

We study the estimation of low rank matrices via nonconvex optimization. Compared with convex relaxation, nonconvex optimization exhibits superior empirical performance for large scale instances of low rank matrix estimation. However, the understanding of its theoretical guarantees are limited. In this paper, we define the notion of projected oracle divergence based on which we establish sufficient conditions for the success of nonconvex optimization. We illustrate the consequences of this general framework for matrix sensing and completion. In particular, we prove that a broad class of nonconvex optimization algorithms, including alternating minimization and gradient-type methods, geometrically converge to the global optimum and exactly recover the true low rank matrices under standard conditions.

We study sparse principal component analysis (sparse PCA) for high dimensional multivariate vector autoregressive (VAR) time series. By treating the transition matrix as a nuisance parameter, we show that sparse PCA can be directly applied on analyzing multivariate time series as if the data are i.i.d. generated. Under a double asymptotic framework in which both the length of the sample period T and dimensionality d of the time series can increase (with possibly d≫T), we provide explicit rates of convergence of the angle between the estimated and population leading eigenvectors of the time series covariance matrix. Our results suggest that the spectral norm of the transition matrix plays a pivotal role in determining the final rates of convergence. Implications of such a general result is further illustrated using concrete examples. The results of this paper have impacts on different applications, including financial time series, biomedical imaging, and social media, etc.