Abstract Many real-world machine learning applications are characterized by a huge number of features, leading to computational and memory issues, as well as the risk of overfitting. Ideally, only relevant and non-redundant features should be considered to preserve the complete information of the data and limit the dimensionality. Dimensionality reduction and feature selection are common preprocessing techniques addressing the challenge of efficiently dealing with high-dimensional data. Dimensionality reduction methods control the number of features in a dataset while minimizing information loss. Feature selection aims to identify the most relevant features for a task, discarding the less informative ones. Previous works have proposed approaches that aggregate features depending on their correlation without discarding any of them and preserving their interpretability through aggregation with the mean. A limitation of these works is the assumption of linearity in the relationship between features and targets. In this paper, we relax this assumption in two ways. First, we propose a bias-variance analysis for general regression models with additive Gaussian noise, leading to a first dimensionality reduction algorithm (NonLinCFA). Then, we extend the approach assuming that a generalized (non-)linear model regulates the data generation process. A deviance analysis leads to a second dimensionality reduction algorithm (GenLinCFA), applicable to larger classes of regression problems and in classification. In both cases, the main focus is to preserve the interpretability of the reduced features through the aggregation with the mean of groups of original features. Finally, we test the algorithms on synthetic and real-world datasets, performing regression and classification and showing competitive performance.

Abstract In reinforcement learning, the performance of an algorithm is typically evaluated along two dimensions: computational and statistical complexity. While theoretical researchers often prioritize statistical efficiency—minimizing the number of samples needed to reach the desired accuracy—practitioners focus mainly on reducing computational costs, such as training time and resource consumption. Bridging these two perspectives requires algorithms able to deliver strong statistical guarantees while remaining computationally efficient in practice. In this paper, we introduce , a meta-algorithm designed to enhance state-of-the-art RL algorithms by improving their computational efficiency while maintaining competitive sample efficiency. is based on the novel notion of W-step Markov decision process (MDP), where, instead of performing a single action and transitioning to the next state, the agent executes a sequence of W actions before observing the resulting state and collecting the discounted W -step cumulative reward. First, we provide a theoretical analysis of the suboptimality introduced in the optimal policy performance when planning in a W -MDP, highlighting the impact of the environment stochasticity. Second, we apply to GPOMDP, a well-known policy gradient method, and theoretically investigate the advantages of learning in the W -MDP in terms of variance reduction and improved sample complexity. Finally, empirical evaluations confirm that reduces computational costs while preserving sample efficiency.

We study goal-conditioned Hierarchical Reinforcement Learning (HRL), where a high-level agent instructs sub-goals to a low-level agent. Under the assumption of a sparse reward function and known hierarchical decomposition, we propose a new algorithm to learn optimal hierarchical policies. Our algorithm takes a low-level policy as input and is flexible enough to work with a wide range of low-level policies. We show that when the algorithm that computes the low-level policy is optimistic and provably efficient, our HRL algorithm enjoys a regret bound which represents a significant improvement compared to previous results for HRL. Importantly, our regret upper bound highlights key characteristics of the hierarchical decomposition that guarantee that our hierarchical algorithm is more efficient than the best monolithic approach. We support our theoretical findings with experiments that underscore that our method consistently outperforms algorithms that ignore the hierarchical structure.

We tackle average-reward infinite-horizon POMDPs with an unknown transition model but a known observation model, a setting that has been previously addressed in two limiting ways: (i) frequentist methods relying on suboptimal stochastic policies having a minimum probability of choosing each action, and (ii) Bayesian approaches employing the optimal policy class but requiring strong assumptions about the consistency of employed estimators. Our work removes these limitations by proving convenient estimation guarantees for the transition model and introducing an optimistic algorithm that leverages the optimal class of deterministic belief-based policies. We introduce modifications to existing estimation techniques providing theoretical guarantees separately for each estimated action transition matrix. Unlike existing estimation methods that are unable to use samples from different policies, we present a novel and simple estimator that overcomes this barrier. This new data-efficient technique, combined with the proposed $\textit{Action-wise OAS-UCRL}$ algorithm and a tighter theoretical analysis, leads to the first approach enjoying a regret guarantee of order $\mathcal{O}(\sqrt{T \log T})$ when compared against the optimal policy, thus improving over state of the art techniques. Finally, theoretical results are validated through numerical simulations showing the efficacy of our method against baseline methods.

The heavy-tailed bandit problem Bubeck et al.,2013 , is a variant of the stochastic multi-armed bandit problem where the reward distributions have finite absolute raw moments of maximum order $1+\epsilon$, uniformly bounded by a constant $u < +\infty$, for some $\epsilon \in (0,1]$. In this setting, most of the proposed approaches crucially rely on the knowledge of both $\epsilon$ and $u$. Recent works have highlighted that adapting to such parameters when they are unknown is harder than adapting to the subgaussian constant or the rewards range in non-heavy-tailed bandits. It is known that it is not possible to adapt to either $\epsilon$ or $u$ without either ($i$) incurring extra regret or ($ii$) enforcing additional assumptions. However, it remains an open question what the best attainable performance is when no additional assumptions are provided. Moreover, the assumptions proposed in the literature are not comparable, as none of them is strictly weaker than the others. Thus, another open question is about the nature of the assumptions needed to compensate for this cost.

The success of sequential decision-making approaches, such as reinforcement learning (RL), is closely tied to the availability of a reward feedback. However, designing a reward function that encodes the desired objective is a challenging task. In this work, we address a more realistic scenario: sequential decision making with preference feedback provided, for instance, by a human expert. We aim to build a theoretical basis linking preferences, (non-Markovian) utilities, and (Markovian) rewards, and we study the connections between them. First, we model preference feedback using a partial (pre)order over trajectories, enabling the presence of incomparabilities that are common when preferences are provided by humans but are surprisingly overlooked in existing works. Second, to provide a theoretical justification for a common practice, we investigate how a preference relation can be approximated by a multi-objective utility. We introduce a notion of preference-utility compatibility and analyze the computational complexity of this transformation, showing that constructing the minimum-dimensional utility is NP-hard. Third, we propose a novel concept of preference-based policy dominance that does not rely on utilities or rewards and discuss the computational complexity of assessing it. Fourth, we develop a computationally efficient algorithm to approximate a utility using (Markovian) rewards and quantify the error in terms of the suboptimality of the optimal policy induced by the approximating reward. This work aims to lay the foundation for a principled approach to sequential decision making from preference feedback, with promising potential applications in RL from human feedback.

In the standard Reinforcement Learning (RL) paradigm, the action space is assumed to be fixed and immutable throughout the learning process. However, in many real-world scenarios, not all actions are available at every decision stage. The available action set may depend on the current environment state, domain-specific constraints, or other (potentially stochastic) factors outside the agent’s control. To address these realistic scenarios, we introduce a novel paradigm called Sleeping Reinforcement Learning, where the available action set varies during the interaction with the environment. We start with the simpler scenario in which the available action sets are revealed at the beginning of each episode. We show that a modification of UCBVI achieves regret of order $\widetilde{\mathcal{O}}(H\sqrt{SAT})$, where $H$ is the horizon, $S$ and $A$ are the cardinalities of the state and action spaces, respectively, and $T$ is the learning horizon. Next, we address the more challenging and realistic scenario in which the available actions are disclosed only at each decision stage. By leveraging a novel construction, we establish a minimax lower bound of order $\Omega(\sqrt{T 2^{A/2}})$ when the availability of actions is governed by a Markovian process, establishing a statistical barrier of the problem. Focusing on the statistically tractable case where action availability depends only on the current state and stage, we propose a new optimistic algorithm that achieves regret guarantees of order $\widetilde{\mathcal{O}}(H\sqrt{SAT})$, showing that the problem shares the same complexity of standard RL.

Although it is well-known that humans commonly engage in risk-sensitive behaviors in the presence of stochasticity, most Inverse Reinforcement Learning (IRL) models assume a risk-neutral agent. As such, beyond $(i)$ introducing model misspecification, $(ii)$ they do not permit direct inference of the risk attitude of the observed agent, which can be useful in many applications. In this paper, we propose a novel model of behavior to cope with these issues. By allowing for risk sensitivity, our model alleviates $(i)$, and by explicitly representing risk attitudes through (learnable) utility functions, it solves $(ii)$. Then, we characterize the partial identifiability of an agent’s utility under the new model and note that demonstrations from multiple environments mitigate the problem. We devise two provably-efficient algorithms for learning utilities in a finite-data regime, and we conclude with some proof-of-concept experiments to validate both our model and our algorithms.

*Policy gradient* (PG) methods are effective *reinforcement learning* (RL) approaches, particularly for continuous problems. While they optimize stochastic (hyper)policies via action- or parameter-space exploration, real-world applications often require deterministic policies. Existing PG convergence guarantees to deterministic policies assume a fixed stochasticity in the (hyper)policy, tuned according to the desired final suboptimality, whereas practitioners commonly use a dynamic stochasticity level. This work provides the theoretical foundations for this practice. We introduce PES, a phase-based method that reduces stochasticity via a deterministic schedule while running PG subroutines with fixed stochasticity in each phase. Under gradient domination assumptions, PES achieves last-iterate convergence to the optimal deterministic policy with a sample complexity of order $\widetilde{\mathcal{O}}(\epsilon^{-5})$. Additionally, we analyze the common practice, termed SL-PG, of jointly learning stochasticity (via an appropriate parameterization) and (hyper)policy parameters. We show that SL-PG also ensures last-iterate convergence with a rate $\widetilde{\mathcal{O}}(\epsilon^{-3})$, but to the optimal stochastic (hyper)policy only, requiring stronger assumptions compared to PES.

*Restless* Multi-Armed Bandits (MABs) are a general framework designed to handle real-world decision-making problems where the expected rewards evolve over time, such as in recommender systems and dynamic pricing. In this work, we investigate from a theoretical standpoint two well-known structured subclasses of restless MABs: the *rising* and the *rising concave* settings, where the expected reward of each arm evolves over time following an unknown *non-decreasing* and a *non-decreasing concave* function, respectively. By providing a novel methodology of independent interest for general restless bandits, we establish new lower bounds on the expected cumulative regret for both settings. In the rising case, we prove a lower bound of order $\Omega(T^{2/3})$, matching known upper bounds for restless bandits; whereas, in the rising concave case, we derive a lower bound of order $\Omega(T^{3/5})$, proving for the first time that this setting is provably more challenging than stationary MABs. Then, we introduce Rising Concave Budgeted Exploration (RC-BE($\alpha$)), a new regret minimization algorithm designed for the rising concave MABs. By devising a novel proof technique, we show that the expected cumulative regret of RC-BE($\alpha$) is in the order of $\widetilde{\mathcal{O}}(T^{7/11})$. These results collectively make a step towards closing the gap in rising concave MABs, positioning them between stationary and general restless bandit settings in terms of statistical complexity.

We address the learning problem in the context of infinite-horizon average-reward POMDPs. Traditionally, this problem has been approached using $\textit{Spectral Decomposition}$ (SD) methods applied to samples collected under non-adaptive policies, such as uniform or round-robin policies. Recently, SD techniques have been extended to accommodate a restricted class of adaptive policies such as $\textit{memoryless policies}$. However, the use of adaptive policies has introduced challenges related to data inefficiency, as SD methods typically require all samples to be drawn from a single policy. In this work, we propose $\texttt{Mixed Spectral Estimation}$, which generalizes spectral estimation techniques to support a broader class of $\textit{belief-based policies}$. We solve the open question of whether spectral methods can be applied to samples collected from multiple policies, and we provide finite-sample guarantees for our approach under standard observability and ergodicity assumptions. Building on this data-efficient estimation method, we introduce the $\texttt{Mixed Spectral UCRL}$ algorithm. Through a refined theoretical analysis, we demonstrate that it achieves a regret bound of $\widetilde{\mathcal{O}}(\sqrt{T})$ when compared to the optimal policy, without requiring full knowledge of either the transition or the observation model. Finally, we present numerical simulations that validate the theoretical analysis of both the proposed estimation procedure and the $\texttt{Mixed Spectral UCRL}$ algorithm.

In this work, we study the statistical properties of the off-policy estimation problem, i.e., estimating expectations under a target policy using samples collected from a different policy. We begin by presenting a novel minimax concentration lower bound that highlights the fundamental limits of off-policy estimation. We then analyze two well-known importance weighting (IW) techniques: vanilla IW and self-normalized importance weighting (SN). For both methods, we derive concentration and anti-concentration results, showing that their concentration rates are provably suboptimal compared to our lower bound. Observing that this undesired behavior arises from the heavy-tailed nature of the IW and SN estimators, we propose a new class of parametric estimators based on a transformation using the power mean (PM), which is no longer heavy-tailed. We study the theoretical properties of the PM estimator in terms of bias and variance. We show that, with suitable (possibly data-driven) tuning of its parameters, the PM estimator satisfies two key properties under certain conditions: ( i ) it achieves a subgaussian concentration rate that matches our lower bound and ( ii ) it maintains differentiability with respect to the target policy. Finally, we validate our approach through numerical simulations on both synthetic datasets and contextual bandits, comparing it against standard off-policy evaluation and learning baselines. 1

In several real-world sequential decision problems, at every step, the learner is required to select different actions. Every action affects a specific part of the system and generates an observable intermediate effect. In this paper, we introduce the Factored-Reward Bandits (FRBs), a novel setting able to effectively capture and exploit the structure of this class of scenarios, where the reward is computed as the product of the action intermediate observations. We characterize the statistical complexity of the learning problem in the FRBs, by deriving worst-case and asymptotic instance-dependent regret lower bounds. Then, we devise and analyze two regret minimization algorithms. The former, F-UCB, is an anytime optimistic approach matching the worst-case lower bound (up to logarithmic factors) but fails to perform optimally from the instance-dependent perspective. The latter, F-Track, is a bound-tracking approach, that enjoys optimal asymptotic instance-dependent regret guarantees. Finally, we study the problem of performing best arm identification in this setting. We derive an error probability lower bound, and we develop F-SR, a nearly optimal rejection-based algorithm for identifying the best action vector, given a time budget.2

The (expected cumulative) regret is the customary index to judge the performance of online sequential decision-making algorithms. In the traditional form, it is defined as the expected sum over a learning horizon T of the sub-optimality gaps ∆It (i.e., expected instantaneous regret) the agent suffers when playing arm It at round t. In this paper, we propose and investigate a generalization of this notion, named g-(expected cumulative) regret, obtained by applying a transformation function g to the sub-optimality gaps, making the agent suffer g(∆It) instead of just ∆It . Intuitively, function g embeds the “perception” that the agent manifests when performing a sub-optimal decision. We first show that sublinear g-regret is not achievable for a generic transformation function g. Then, we introduce a mild condition on g and provide instance-dependent and worst-case (i.e., minimax) lower bounds for the g-regret. Finally, we show that state-of-the-art stochastic bandit algorithms with no modification surprisingly display optimal performances for the g-regret. Specifically, we prove that UCB1 matches (up to constant factors) the instance-dependent lower bound regardless of function g and that MOSS matches (up to constant factors) the minimax lower bound at least for a wide class of transformation functions.

Inverse reinforcement learning (IRL) has seen significant advancements in recent years. This class of approaches aims to efficiently learn the underlying reward function that rationalizes the behavior exhibited by expert agents, often represented by humans. In contrast to mere behavioral cloning, the reconstruction of a reward function yields appealing implications, as it allows for more effective interpretability of the expert’s decisions and provides a transferable specification of the expert’s objectives for application in even different environments. Unlike the well-understood field of reinforcement learning (RL) from a theoretical perspective, IRL still grapples with limited understanding, significantly constraining its applicability. A fundamental challenge in IRL is the inherent ambiguity in selecting a reward function, given the existence of multiple candidate functions, all explaining the expert’s behavior. In this talk, I will survey three of my papers that have made notable contributions to the IRL field: “Provably Efficient Learning of Transferable Rewards”, “Towards Theoretical Understanding of Inverse Reinforcement Learning”, and “Inverse Reinforcement Learning with Sub-optimal Experts". The central innovation introduced by the first paper is a novel formulation of the IRL problem that overcomes the issue of ambiguity. IRL is reframed as the problem of learning the feasible reward set, which is the set of all rewards that can explain the expert’s behavior. This approach postpones the selection of the reward function, thereby circumventing the ambiguity issues. Furthermore, the feasible reward set exhibits convenient geometric properties that enable the development of efficient algorithms for its computation. Building on this novel formulation of IRL, the second paper addresses the problem of efficiently learning the feasible reward set when the environment and the expert’s policy are not known in advance. It introduces a novel way to assess the dissimilarity between feasible reward sets based on the Hausdorff distance and presents a new PAC (probabilistic approximately correct) framework. The most significant contribution of this paper is the introduction of the first sample complexity lower bound, which highlights the challenges inherent in the IRL problem. Deriving this lower bound necessitated the development of novel technical tools. The paper also demonstrates that when a generative model of the environment is available, a uniform sampling strategy achieves a sample complexity that matches the lower bound, up to logarithmic factors. Finally, in the third paper, the IRL problem in the presence of sub-optimal experts is investigated. Specifically, the paper assumes the availability of multiple sub-optimal experts, in addition to the expert agent, which provides additional demonstrations, associated with a known quantification of the maximum amount of sub-optimality. The paper shows that this richer information mitigates the ambiguity problem, significantly reducing the size of the feasible reward set while retaining its favorable geometric properties. Furthermore, the paper explores the associated statistical problem and derives novel lower bounds for sample complexity, along with almost matching algorithms. These selected papers represent notable advancements in IRL, contributing to the establishment of a solid theoretical foundation for IRL and extending the framework to accommodate scenarios with sub-optimal experts.

Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an iterated procedure where each step consists of (i) an application of the Bellman operator and (ii) a projection step into a considered function space. Notoriously, the Bellman operator leverages transition samples, which strongly determine its behavior, as uninformative samples can result in negligible updates or long detours, whose detrimental effects are further exacerbated by the computationally intensive projection step. To address these issues, we propose a novel alternative approach based on learning an approximate version of the Bellman operator rather than estimating it through samples as in AVI approaches. This way, we are able to (i) generalize across transition samples and (ii) avoid the computationally intensive projection step. For this reason, we call our novel operator projected Bellman operator (PBO). We formulate an optimization problem to learn PBO for generic sequential decision-making problems, and we theoretically analyze its properties in two representative classes of RL problems. Furthermore, we theoretically study our approach under the lens of AVI and devise algorithmic implementations to learn PBO in offline and online settings by leveraging neural network parameterizations. Finally, we empirically showcase the benefits of PBO w.r.t. the regular Bellman operator on several RL problems.

Autoregressive processes naturally arise in a large variety of real-world scenarios, including stock markets, sales forecasting, weather prediction, advertising, and pricing. When facing a sequential decision-making problem in such a context, the temporal dependence between consecutive observations should be properly accounted for guaranteeing convergence to the optimal policy. In this work, we propose a novel online learning setting, namely, Autoregressive Bandits (ARBs), in which the observed reward is governed by an autoregressive process of order $k$, whose parameters depend on the chosen action. We show that, under mild assumptions on the reward process, the optimal policy can be conveniently computed. Then, we devise a new optimistic regret minimization algorithm, namely, AutoRegressive Upper Confidence Bound (AR-UCB), that suffers sublinear regret of order $\tilde{O} ( \frac{(k+1)^{3/2}\sqrt{nT}}{(1-\Gamma)^2} )$, where $T$ is the optimization horizon, $n$ is the number of actions, and $\Gamma < 1$ is a stability index of the process. Finally, we empirically validate our algorithm, illustrating its advantages w.r.t. bandit baselines and its robustness to misspecification of key parameters.

We study a novel sequential decision-making setting, namely the dissimilarity bandits. At each round, the learner pulls an arm that provides a stochastic d-dimensional observation vector. The learner aims to identify the pair of arms with the maximum dissimilarity, where such an index is computed over pairs of expected observation vectors. We propose Successive Elimination for Dissimilarity (SED), a fixed-confidence best-pair identification algorithm based on sequential elimination. SED discards individual arms when there is statistical evidence that they cannot belong to a pair of most dissimilar arms and, thus, effectively exploits the structure of the setting by reusing the estimates of the expected observation vectors. We provide results on the sample complexity of SED, depending on {HP}, a novel index characterizing the complexity of identifying the pair of the most dissimilar arms. Then, we provide a sample complexity lower bound, highlighting the challenges of the identification problem for dissimilarity bandits, which is almost matched by our SED. Finally, we compare our approach over synthetically generated data and a realistic environmental monitoring domain against classical and combinatorial best-arm identification algorithms for the cases $d=1$ and $d>1$.

Heavy-tailed distributions naturally arise in several settings, from finance to telecommunications. While regret minimization under subgaussian or bounded rewards has been widely studied, learning with heavy-tailed distributions only gained popularity over the last decade. In this paper, we consider the setting in which the reward distributions have finite absolute raw moments of maximum order $1+\epsilon$, uniformly bounded by a constant $u<+\infty$, for some $\epsilon \in (0,1]$. In this setting, we study the regret minimization problem when $\epsilon$ and $u$ are unknown to the learner and it has to adapt. First, we show that adaptation comes at a cost and derive two negative results proving that the same regret guarantees of the non-adaptive case cannot be achieved with no further assumptions. Then, we devise and analyze a fully data-driven trimmed mean estimator and propose a novel adaptive regret minimization algorithm, \texttt{AdaR-UCB}, that leverages such an estimator. Finally, we show that \texttt{AdaR-UCB} is the first algorithm that, under a known distributional assumption, enjoys regret guarantees nearly matching those of the non-adaptive heavy-tailed case.

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample complexity by performing a simple, \emph{perturbed} version of least-squares value iteration with orthogonal trigonometric polynomials as features. Key to our solution is a novel projection technique based on ideas from harmonic analysis. Our $\widetilde{O}(\epsilon^{-2-d/(\nu+1)})$ sample complexity, where $d$ is the dimension of the state-action space and $\nu$ the order of smoothness, recovers the state-of-the-art result of discretization approaches for the special case of Lipschitz MDPs $(\nu=0)$. At the same time, for $\nu\to\infty$, it recovers and greatly generalizes the $O(\epsilon^{-2})$ rate of low-rank MDPs, which are more amenable to regression approaches. In this sense, our result bridges the gap between two popular but conflicting perspectives on continuous-space MDPs.

In this paper, we propose a novel generalization of rested and restless bandits where the evolution of the arms’ expected rewards is governed by a graph defined over the arms. An edge connecting a pair of arms $(i,j)$ represents the fact that a pull of arm $i$ triggers the evolution of arm $j$, and vice versa. Interestingly, rested and restless bandits are both special cases of our model for some suitable (degenerate) graphs. Still, the model can represent way more general and interesting scenarios. We first tackle the problem of computing the optimal policy when no specific structure is assumed on the graph, showing that it is NP-hard. Then, we focus on a specific structure forcing the graph to be composed of a set of fully connected subgraphs (i.e., cliques), and we prove that the optimal policy can be easily computed in closed form. Then, we move to the learning problem presenting regret minimization algorithms for deterministic and stochastic cases. Our regret bounds highlight the complexity of the learning problem by incorporating instance-dependent terms that encode specific properties of the underlying graph structure. Moreover, we illustrate how the knowledge of the underlying graph is not necessary for achieving the no-regret property.

*Inverse reinforcement learning* (IRL) aims to recover the reward function of an *expert* agent from demonstrations of behavior. It is well-known that the IRL problem is fundamentally ill-posed, i.e., many reward functions can explain the demonstrations. For this reason, IRL has been recently reframed in terms of estimating the *feasible reward set* (Metelli et al., 2021), thus, postponing the selection of a single reward. However, so far, the available formulations and algorithmic solutions have been proposed and analyzed mainly for the *online* setting, where the learner can interact with the environment and query the expert at will. This is clearly unrealistic in most practical applications, where the availability of an *offline* dataset is a much more common scenario. In this paper, we introduce a novel notion of feasible reward set capturing the opportunities and limitations of the offline setting and we analyze the complexity of its estimation. This requires the introduction an original learning framework that copes with the intrinsic difficulty of the setting, for which data coverage is not under control. Then, we propose two computationally and statistically efficient algorithms, IRLO and PIRLO, for addressing the problem. In particular, the latter adopts a specific form of *pessimism* to enforce the novel, desirable property of *inclusion monotonicity* of the delivered feasible set. With this work, we aim to provide a panorama of the challenges of the offline IRL problem and how they can be fruitfully addressed.

Obtaining no-regret guarantees for reinforcement learning (RL) in the case of problems with continuous state and/or action spaces is still one of the major open challenges in the field. Recently, a variety of solutions have been proposed, but besides very specific settings, the general problem remains unsolved. In this paper, we introduce a novel structural assumption on the Markov decision processes (MDPs), namely $\nu-$smoothness, that generalizes most of the settings proposed so far (e.g., linear MDPs and Lipschitz MDPs). To face this challenging scenario, we propose two algorithms for regret minimization in $\nu-$smooth MDPs. Both algorithms build upon the idea of constructing an MDP representation through an orthogonal feature map based on Legendre polynomials. The first algorithm, Legendre-Eleanor, archives the no-regret property under weaker assumptions but is computationally inefficient, whereas the second one, Legendre-LSVI, runs in polynomial time, although for a smaller class of problems. After analyzing their regret properties, we compare our results with state-of-the-art ones from RL theory, showing that our algorithms achieve the best guarantees.

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters. Stochastic controllers, however, are often undesirable from a practical perspective because of their lack of robustness, safety, and traceability. In common practice, stochastic (hyper)policies are learned only to deploy their deterministic version. In this paper, we make a step towards the theoretical understanding of this practice. After introducing a novel framework for modeling this scenario, we study the global convergence to the best deterministic policy, under (weak) gradient domination assumptions. Then, we illustrate how to tune the exploration level used for learning to optimize the trade-off between the sample complexity and the performance of the deployed deterministic policy. Finally, we quantitatively compare action-based and parameter-based exploration, giving a formal guise to intuitive results.

In several real-world sequential decision problems, at every step, the learner is required to select different actions. Every action affects a specific part of the system and generates an observable intermediate effect. In this paper, we introduce the Factored-Reward Bandits (FRBs), a novel setting able to effectively capture and exploit the structure of this class of scenarios, where the reward is computed as the product of the action intermediate observations. We characterize the statistical complexity of the learning problem in the FRBs, by deriving worst-case and asymptotic instance-dependent regret lower bounds. Then, we devise and analyze two regret minimization algorithms. The former, F-UCB, is an anytime optimistic approach matching the worst-case lower bound (up to logarithmic factors) but fails to perform optimally from the instance-dependent perspective. The latter, F-Track, is a bound-tracking approach, that enjoys optimal asymptotic instance-dependent regret guarantees.

Stochastic Rising Bandits (SRBs) model sequential decision-making problems in which the expected reward of the available options increases every time they are selected. This setting captures a wide range of scenarios in which the available options are learning entities whose performance improves (in expectation) over time (e.g., online best model selection). While previous works addressed the regret minimization problem, this paper focuses on the fixed-budget Best Arm Identification (BAI) problem for SRBs. In this scenario, given a fixed budget of rounds, we are asked to provide a recommendation about the best option at the end of the identification process. We propose two algorithms to tackle the above-mentioned setting, namely R-UCBE, which resorts to a UCB-like approach, and R-SR, which employs a successive reject procedure. Then, we prove that, with a sufficiently large budget, they provide guarantees on the probability of properly identifying the optimal option at the end of the learning process and on the simple regret. Furthermore, we derive a lower bound on the error probability, matched by our R-SR (up to constants), and illustrate how the need for a sufficiently large budget is unavoidable in the SRB setting. Finally, we numerically validate the proposed algorithms in both synthetic and realistic environments.

Machine learning algorithms are designed to capture complex relationships between features. In this context, the high dimensionality of data often results in poor model performance, with the risk of overfitting. Feature selection, the process of selecting a subset of relevant and non-redundant features, is an essential step to mitigate these issues. However, classical feature selection approaches do not inspect the causal relationship between features and the target variable, which can lead to misleading results in real-world applications. Causal discovery, instead, aims to identify causal relationships between features with observational data. In this paper, we propose a novel methodology at the intersection between feature selection and causal discovery, focusing on time series. We introduce a causal feature selection approach that relies on the forward and backward feature selection procedures and leverages transfer entropy to estimate the causal flow of information. In this context, we provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases. Finally, we present numerical validations on synthetic and real-world regression problems, showing results competitive w.r.t. the considered baselines.

Feeders play a crucial role in efficiently transporting materials, parts, and components to work areas in manufacturing industries. They employ various technologies and mechanisms tailored to the specific requirements of the manufacturing process. With the growing demand for flexibility and technology across diverse applications, feeders are evolving into smarter systems, thanks to the integration of industrial robots into their architecture. The challenges associated with grasping tasks, such as object variability, environmental dynamics, and real-time adaptability, underscore the need for advanced cognitive capabilities. Consequently, the application of Reinforcement Learning (RL) becomes instrumental in enabling robots to learn and adapt their grasping strategies autonomously. When combined with Deep Learning (DL), RL techniques drive robots to refine their grasping actions through iterative experiences, ultimately enhancing overall performance and dexterity. The primary goal of this work is to establish a comprehensive pipeline, starting from the 3D model of the object to be grasped and culminating in a trained algorithm capable of managing the hierarchical nature of agents. These agents detect the object to grasp and make decisions regarding the suggested point of picking. This complete workflow facilitates a seamless transition between graspable objects, introducing new flexible capabilities to a smart feeder equipped with an industrial robot. As a result, the integration of RL and DL not only addresses the inherent challenges in grasping tasks but also empowers the feeder system to adapt to a variety of objects dynamically, thereby optimizing efficiency in a manufacturing setting.

In online Inverse Reinforcement Learning (IRL), the learner can collect samples about the dynamics of the environment to improve its estimate of the reward function. Since IRL suffers from identifiability issues, many theoretical works on online IRL focus on estimating the entire set of rewards that explain the demonstrations, named the *feasible reward set*. However, none of the algorithms available in literature can scale to problems with large state spaces. In this paper, we focus on the online IRL problem in Linear Markov Decision Processes (MDPs). We show that the structure offered by Linear MDPs is not sufficient for efficiently estimating the feasible set when the state space is large. As a consequence, we introduce the novel framework of *rewards compatibility*, which generalizes the notion of feasible set, and we develop CATY-IRL, a sample efficient algorithm whose complexity is independent of the size of the state space in Linear MDPs. When restricted to the tabular setting, we demonstrate that CATY-IRL is minimax optimal up to logarithmic factors. As a by-product, we show that Reward-Free Exploration (RFE) enjoys the same worst-case rate, improving over the state-of-the-art lower bound. Finally, we devise a unifying framework for IRL and RFE that may be of independent interest.

Achieving the no-regret property for Reinforcement Learning (RL) problems in continuous state and action-space environments is one of the major open problems in the field. Existing solutions either work under very specific assumptions or achieve bounds that are vacuous in some regimes. Furthermore, many structural assumptions are known to suffer from a provably unavoidable exponential dependence on the time horizon $H$ in the regret, which makes any possible solution unfeasible in practice. In this paper, we identify _local linearity_ as the feature that makes Markov Decision Processes (MDPs) both _learnable_ (sublinear regret) and _feasible_ (regret that is polynomial in $H$). We define a novel MDP representation class, namely _Locally Linearizable MDPs_, generalizing other representation classes like Linear MDPs and MDPS with low inherent Belmman error. Then, i) we introduce **Cinderella**, a no-regret algorithm for this general representation class, and ii) we show that all known learnable and feasible MDP families are representable in this class. We first show that all known feasible MDPs belong to a family that we call _Mildly Smooth MDPs_. Then, we show how any mildly smooth MDP can be represented as a Locally Linearizable MDP by an appropriate choice of representation. This way, **Cinderella** is shown to achieve state-of-the-art regret bounds for all previously known (and some new) continuous MDPs for which RL is learnable and feasible.

*Constrained Reinforcement Learning* (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated on expected costs. In this setting, *policy-based* methods are widely used since they come with several advantages when dealing with continuous-control problems. These methods search in the policy space with an *action-based* or *parameter-based* exploration strategy, depending on whether they learn directly the parameters of a stochastic policy or those of a stochastic hyperpolicy. In this paper, we propose a general framework for addressing CRL problems via *gradient-based primal-dual* algorithms, relying on an alternate ascent/descent scheme with dual-variable regularization. We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-iterate convergence guarantees under (weak) gradient domination assumptions, improving and generalizing existing results. Then, we design C-PGAE and C-PGPE, the action-based and the parameter-based versions of C-PG, respectively, and we illustrate how they naturally extend to constraints defined in terms of *risk measures* over the costs, as it is often requested in safety-critical scenarios. Finally, we numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines, demonstrating their effectiveness.

Inverse Reinforcement Learning (IRL) deals with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act *optimally* in an underlying unknown task. Recent works have studied the IRL problem from the perspective of recovering the *feasible reward set*, i.e., the class of reward functions that are compatible with a unique optimal expert. However, in several problems of interest it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we focus on the reconstruction of the feasible reward set when, in addition to demonstrations from the optimal expert, we observe the behavior of multiple *sub-optimal experts*. Given this problem, we first study the theoretical properties showing that the presence of multiple sub-optimal experts, in addition to the optimal one, can significantly shrink the set of compatible rewards, ultimately mitigating the inherent ambiguity of IRL. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model and analyze a uniform sampling algorithm that turns out to be minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to that of the optimal expert.

In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the algorithm can choose to sample an arm at a lower fidelity (less accurate mean estimate) for a lower cost. Several methods have been proposed for tackling this problem, but their optimality remain elusive, notably due to loose lower bounds on the total cost needed to identify the best arm. Our first contribution is a tight, instance-dependent lower bound on the cost complexity. The study of the optimization problem featured in the lower bound provides new insights to devise computationally efficient algorithms, and leads us to propose a gradient-based approach with asymptotically optimal cost complexity. We demonstrate the benefits of the new algorithm compared to existing methods in experiments. Our theoretical and empirical findings also shed light on an intriguing concept of optimal fidelity for each arm.

Abstract One of the central issues of several machine learning applications on real data is the choice of the input features. Ideally, the designer should select a small number of the relevant, nonredundant features to preserve the complete information contained in the original dataset, with little collinearity among features. This procedure helps mitigate problems like overfitting and the curse of dimensionality, which arise when dealing with high-dimensional problems. On the other hand, it is not desirable to simply discard some features, since they may still contain information that can be exploited to improve results. Instead, dimensionality reduction techniques are designed to limit the number of features in a dataset by projecting them into a lower dimensional space, possibly considering all the original features. However, the projected features resulting from the application of dimensionality reduction techniques are usually difficult to interpret. In this paper, we seek to design a principled dimensionality reduction approach that maintains the interpretability of the resulting features. Specifically, we propose a bias-variance analysis for linear models and we leverage these theoretical results to design an algorithm, Linear Correlated Features Aggregation (LinCFA), which aggregates groups of continuous features with their average if their correlation is “sufficiently large”. In this way, all features are considered, the dimensionality is reduced and the interpretability is preserved. Finally, we provide numerical validations of the proposed algorithm both on synthetic datasets to confirm the theoretical results and on real datasets to show some promising applications.

This work addresses the mediator feedback problem, a bandit game where the decision set consists of a number of policies, each associated with a probability distribution over a common space of outcomes. Upon choosing a policy, the learner observes an outcome sampled from its distribution and incurs the loss assigned to this outcome in the present round. We introduce the policy set capacity as an information-theoretic measure for the complexity of the policy set. Adopting the classical EXP4 algorithm, we provide new regret bounds depending on the policy set capacity in both the adversarial and the stochastic settings. For a selection of policy set families, we prove nearly-matching lower bounds, scaling similarly with the capacity. We also consider the case when the policies' distributions can vary between rounds, thus addressing the related bandits with expert advice problem, which we improve upon its prior results. Additionally, we prove a lower bound showing that exploiting the similarity between the policies is not possible in general under linear bandit feedback. Finally, for a full-information variant, we provide a regret bound scaling with the information radius of the policy set.

With the continuous growth of the global economy and markets, resource imbalance has risen to be one of the central issues in real logistic scenarios. In marine transportation, this trade imbalance leads to Empty Container Repositioning (ECR) problems. Once the freight has been delivered from an exporting country to an importing one, the laden will turn into empty containers that need to be repositioned to satisfy new goods requests in exporting countries. In such problems, the performance that any cooperative repositioning policy can achieve strictly depends on the routes that vessels will follow (i.e., fleet deployment). Historically, Operation Research (OR) approaches were proposed to jointly optimize the repositioning policy along with the fleet of vessels. However, the stochasticity of future supply and demand of containers, together with black-box and non-linear constraints that are present within the environment, make these approaches unsuitable for these scenarios. In this paper, we introduce a novel framework, Configurable Semi-POMDPs, to model this type of problems. Furthermore, we provide a two-stage learning algorithm, “Configure & Conquer” (CC), that first configures the environment by finding an approximation of the optimal fleet deployment strategy, and then “conquers” it by learning an ECR policy in this tuned environmental setting. We validate our approach in large and real-world instances of the problem. Our experiments highlight that CC avoids the pitfalls of OR methods and that it is successful at optimizing both the ECR policy and the fleet of vessels, leading to superior performance in world trade environments.

Uncertainty quantification has been extensively used as a means to achieve efficient directed exploration in Reinforcement Learning (RL). However, state-of-the-art methods for continuous actions still suffer from high sample complexity requirements. Indeed, they either completely lack strategies for propagating the epistemic uncertainty throughout the updates, or they mix it with aleatoric uncertainty while learning the full return distribution (e.g., distributional RL). In this paper, we propose Wasserstein Actor-Critic (WAC), an actor-critic architecture inspired by the recent Wasserstein Q-Learning (WQL), that employs approximate Q-posteriors to represent the epistemic uncertainty and Wasserstein barycenters for uncertainty propagation across the state-action space. WAC enforces exploration in a principled way by guiding the policy learning process with the optimization of an upper bound of the Q-value estimates. Furthermore, we study some peculiar issues that arise when using function approximation, coupled with the uncertainty estimation, and propose a regularized loss for the uncertainty estimation. Finally, we evaluate our algorithm on standard MujoCo tasks as well as suite of continuous-actions domains, where exploration is crucial, in comparison with state-of-the-art baselines. Additional details and results can be found in the supplementary material with our Arxiv preprint.

Behavioral Cloning (BC) aims at learning a policy that mimics the behavior demonstrated by an expert. The current theoretical understanding of BC is limited to the case of finite actions. In this paper, we study BC with the goal of providing theoretical guarantees on the performance of the imitator policy in the case of continuous actions. We start by deriving a novel bound on the performance gap based on Wasserstein distance, applicable for continuous-action experts, holding under the assumption that the value function is Lipschitz continuous. Since this latter condition is hardy fulfilled in practice, even for Lipschitz Markov Decision Processes and policies, we propose a relaxed setting, proving that value function is always H\"older continuous. This result is of independent interest and allows obtaining in BC a general bound for the performance of the imitator policy. Finally, we analyze noise injection, a common practice in which the expert's action is executed in the environment after the application of a noise kernel. We show that this practice allows deriving stronger performance guarantees, at the price of a bias due to the noise addition.

In Reinforcement Learning, the performance of learning agents is highly sensitive to the choice of time discretization. Agents acting at high frequencies have the best control opportunities, along with some drawbacks, such as possible inefficient exploration and vanishing of the action advantages. The repetition of the actions, i.e., action persistence, comes into help, as it allows the agent to visit wider regions of the state space and improve the estimation of the action effects. In this work, we derive a novel operator, the All-Persistence Bellman Operator, which allows an effective use of both the low-persistence experience, by decomposition into sub-transition, and the high-persistence experience, thanks to the introduction of a suitable bootstrap procedure. In this way, we employ transitions collected at any time scale to update simultaneously the action values of the considered persistence set. We prove the contraction property of the All-Persistence Bellman Operator and, based on it, we extend classic Q-learning and DQN. After providing a study on the effects of persistence, we experimentally evaluate our approach in both tabular contexts and more challenging frameworks, including some Atari games.

The most relevant problems in discounted reinforcement learning involve estimating the mean of a function under the stationary distribution of a Markov reward process, such as the expected return in policy evaluation, or the policy gradient in policy optimization. In practice, these estimates are produced through a finite-horizon episodic sampling, which neglects the mixing properties of the Markov process. It is mostly unclear how this mismatch between the practical and the ideal setting affects the estimation, and the literature lacks a formal study on the pitfalls of episodic sampling, and how to do it optimally. In this paper, we present a minimax lower bound on the discounted mean estimation problem that explicitly connects the estimation error with the mixing properties of the Markov process and the discount factor. Then, we provide a statistical analysis on a set of notable estimators and the corresponding sampling procedures, which includes the finite-horizon estimators often used in practice. Crucially, we show that estimating the mean by directly sampling from the discounted kernel of the Markov process brings compelling statistical properties w.r.t. the alternative estimators, as it matches the lower bound without requiring a careful tuning of the episode horizon.

Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a reward function justifying the behavior demonstrated by an expert agent. A well-known limitation of IRL is the ambiguity in the choice of the reward function, due to the existence of multiple rewards that explain the observed behavior. This limitation has been recently circumvented by formulating IRL as the problem of estimating the feasible reward set, i.e., the region of the rewards compatible with the expert's behavior. In this paper, we make a step towards closing the theory gap of IRL in the case of finite-horizon problems with a generative model. We start by formally introducing the problem of estimating the feasible reward set, the corresponding PAC requirement, and discussing the properties of particular classes of rewards. Then, we provide the first minimax lower bound on the sample complexity for the problem of estimating the feasible reward set of order ${\Omega}\left( \frac{H^3SA}{\epsilon^2} \left( \log \left(\frac{1}{\delta}\right) + S \right)\right)$, being $S$ and $A$ the number of states and actions respectively, $H$ the horizon, $\epsilon$ the desired accuracy, and $\delta$ the confidence. We analyze the sample complexity of a uniform sampling strategy (US-IRL), proving a matching upper bound up to logarithmic factors. Finally, we outline several open questions in IRL and propose future research directions.

In many real-world sequential decision-making problems, an action does not immediately reflect on the feedback and spreads its effects over a long time frame. For instance, in online advertising, investing in a platform produces an instantaneous increase of awareness, but the actual reward, i.e., a conversion, might occur far in the future. Furthermore, whether a conversion takes place depends on: how fast the awareness grows, its vanishing effects, and the synergy or interference with other advertising platforms. Previous work has investigated the Multi-Armed Bandit framework with the possibility of delayed and aggregated feedback, without a particular structure on how an action propagates in the future, disregarding possible dynamical effects. In this paper, we introduce a novel setting, the Dynamical Linear Bandits (DLB), an extension of the linear bandits characterized by a hidden state. When an action is performed, the learner observes a noisy reward whose mean is a linear function of the hidden state and of the action. Then, the hidden state evolves according to linear dynamics, affected by the performed action too. We start by introducing the setting, discussing the notion of optimal policy, and deriving an expected regret lower bound. Then, we provide an optimistic regret minimization algorithm, Dynamical Linear Upper Confidence Bound (DynLin-UCB), that suffers an expected regret of order $\widetilde{\mathcal{O}} \Big( \frac{d \sqrt{T}}{(1-\overline{\rho})^{3/2}} \Big)$, where $\overline{\rho}$ is a measure of the stability of the system, and $d$ is the dimension of the action vector. Finally, we conduct a numerical validation on a synthetic environment and on real-world data to show the effectiveness of DynLin-UCB in comparison with several baselines.

In Reinforcement Learning (RL), an agent acts in an unknown environment to maximize the expected cumulative discounted sum of an external reward signal, i.e., the expected return. In practice, in many tasks of interest, such as policy optimization, the agent usually spends its interaction budget by collecting episodes of *fixed length* within a simulator (i.e., Monte Carlo simulation). However, given the discounted nature of the RL objective, this data collection strategy might not be the best option. Indeed, the rewards taken in early simulation steps weigh exponentially more than future rewards. Taking a cue from this intuition, in this paper, we design an a-priori budget allocation strategy that leads to the collection of trajectories of different lengths, i.e., *truncated*. The proposed approach provably minimizes the width of the confidence intervals around the empirical estimates of the expected return of a policy. After discussing the theoretical properties of our method, we make use of our trajectory truncation mechanism to extend Policy Optimization via Importance Sampling (POIS, Metelli et al., 2018) algorithm. Finally, we conduct a numerical comparison between our algorithm and POIS: the results are consistent with our theory and show that an appropriate truncation of the trajectories can succeed in improving performance.

We investigate the problem of bandits with expert advice when the experts are fixed and known distributions over the actions. Improving on previous analyses, we show that the regret in this setting is controlled by information-theoretic quantities that measure the similarity between experts. In some natural special cases, this allows us to obtain the first regret bound for EXP4 that can get arbitrarily close to zero if the experts are similar enough. While for a different algorithm, we provide another bound that describes the similarity between the experts in terms of the KL-divergence, and we show that this bound can be smaller than the one of EXP4 in some cases. Additionally, we provide lower bounds for certain classes of experts showing that the algorithms we analyzed are nearly optimal in some cases.

Policy evaluation via Monte Carlo (MC) simulation is at the core of many MC Reinforcement Learning (RL) algorithms (e.g., policy gradient methods). In this context, the designer of the learning system specifies an interaction budget that the agent usually spends by collecting trajectories of *fixed length* within a simulator. However, is this data collection strategy the best option? To answer this question, in this paper, we consider as quality index the variance of an unbiased policy return estimator that uses trajectories of different lengths, i.e., *truncated*. We first derive a closed-form expression of this variance that clearly shows the sub-optimality of the fixed-length trajectory schedule. Furthermore, it suggests that adaptive data collection strategies that spend the available budget sequentially might be able to allocate a larger portion of transitions in timesteps in which more accurate sampling is required to reduce the variance of the final estimate. Building on these findings, we present an *adaptive* algorithm called **R**obust and **I**terative **D**ata collection strategy **O**ptimization (RIDO). The main intuition behind RIDO is to split the available interaction budget into mini-batches. At each round, the agent determines the most convenient schedule of trajectories that minimizes an empirical and robust estimate of the estimator's variance. After discussing the theoretical properties of our method, we conclude by assessing its performance across multiple domains. Our results show that RIDO can adapt its trajectory schedule toward timesteps where more sampling is required to increase the quality of the final estimation.

The Maximum Entropy (Max-Ent) framework has been effectively employed in a variety of Reinforcement Learning (RL) tasks. In this paper, we first propose a novel Max-Ent framework for policy evaluation in a distributional RL setting, named *Distributional Maximum Entropy Policy Evaluation* (D-Max-Ent PE). We derive a generalization-error bound that depends on the complexity of the representation employed, showing that this framework can explicitly take into account the features used to represent the state space while evaluating a policy. Then, we exploit these favorable properties to drive the representation learning of the state space in a Structural Risk Minimization fashion. We employ state-aggregation functions as feature functions and we specialize the D-Max-Ent approach into an algorithm, named *D-Max-Ent Progressive Factorization*, which constructs a progressively finer-grained representation of the state space by balancing the trade-off between preserving information (bias) and reducing the effective number of states, i.e., the complexity of the representation space (variance). Finally, we report the results of some illustrative numerical simulations, showing that the proposed algorithm matches the expected theoretical behavior and highlighting the relationship between aggregations and sample regimes.

Off-policy methods are the basis of a large number of effective Policy Optimization (PO) algorithms. In this setting, Importance Sampling (IS) is typically employed for off-policy evaluation, with the goal of estimating the performance of a target policy, given samples collected with a different behavioral policy. However, in Monte Carlo simulation, IS represents a variance minimization approach. In this field, a suitable behavioral distribution is employed for sampling, allowing diminishing the variance of the estimator below the one achievable when sampling from the target distribution. In this paper, we analyze IS in these two guises in the context of PO. We provide a novel view of off-policy PO, showing a connection between the policy improvement and variance minimization objectives. Then, we illustrate how minimizing the off-policy variance can, in some circumstances, lead to a policy improvement, with the advantage, compared with direct off-policy learning, of implicitly enforcing a trust region. Finally, we present numerical simulations on continuous RL benchmarks, with a particular focus on the robustness to small batch sizes.

Automated Reinforcement Learning (AutoRL) is a relatively new area of research that is gaining increasing attention. The objective of AutoRL consists in easing the employment of Reinforcement Learning (RL) techniques for the broader public by alleviating some of its main challenges, including data collection, algorithm selection, and hyper-parameter tuning. In this work, we propose a general and flexible framework, namely ARLO: Automated Reinforcement Learning Optimizer, to construct automated pipelines for AutoRL. Based on this, we propose a pipeline for offline and one for online RL, discussing the components, interaction, and highlighting the difference between the two settings. Furthermore, we provide a Python implementation of such pipelines, released as an open-source library. Our implementation is tested on an illustrative LQG domain and on classic MuJoCo environments, showing the ability to reach competitive performances requiring limited human intervention. We also showcase the full pipeline on a realistic dam environment, automatically performing the feature selection and the model generation tasks.

Distribution drift is an important issue for practical applications of machine learning (ML). In particular, in streaming ML, the data distribution may change over time, yielding the problem of concept drift, which affects the performance of learners trained with outdated data. In this article, we focus on supervised problems in an online nonstationary setting, introducing a novel learner-agnostic algorithm for drift adaptation, namely importance weighting for drift adaptation (IWDA), with the goal of performing efficient retraining of the learner when drift is detected. IWDA incrementally estimates the joint probability density of input and target for the incoming data and, as soon as drift is detected, retrains the learner using importance-weighted empirical risk minimization. The importance weights are computed for all the samples observed so far, employing the estimated densities, thus, using all available information efficiently. After presenting our approach, we provide a theoretical analysis in the abrupt drift setting. Finally, we present numerical simulations that illustrate how IWDA competes and often outperforms state-of-the-art stream learning techniques, including adaptive ensemble methods, on both synthetic and real-world data benchmarks.

Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an approach which learns a hyper-policy, whose input is time, that outputs the parameters of the policy to be queried at that time. This hyper-policy is trained to maximize the estimated future performance, efficiently reusing past data by means of importance sampling, at the cost of introducing a controlled bias. We combine the future performance estimate with the past performance to mitigate catastrophic forgetting. To avoid overfitting the collected data, we derive a differentiable variance bound that we embed as a penalization term. Finally, we empirically validate our approach, in comparison with state-of-the-art algorithms, on realistic environments, including water resource management and trading.

We propose a novel formulation for the Inverse Reinforcement Learning (IRL) problem, which jointly accounts for the compatibility with the expert behavior of the identified reward and its effectiveness for the subsequent forward learning phase. Albeit quite natural, especially when the final goal is apprenticeship learning (learning policies from an expert), this aspect has been completely overlooked by IRL approaches so far. We propose a new model-free IRL method that is remarkably able to autonomously find a trade-off between the error induced on the learned policy when potentially choosing a sub-optimal reward, and the estimation error caused by using finite samples in the forward learning phase, which can be controlled by explicitly optimizing also the discount factor of the related learning problem. The approach is based on a min-max formulation for the robust selection of the reward parameters and the discount factor so that the distance between the expert’s policy and the learned policy is minimized in the successive forward learning task when a finite and possibly small number of samples is available. Differently from the majority of other IRL techniques, our approach does not involve any planning or forward Reinforcement Learning problems to be solved. After presenting the formulation, we provide a numerical scheme for the optimization, and we show its effectiveness on an illustrative numerical case.

This paper is in the field of stochastic Multi-Armed Bandits (MABs), i.e., those sequential selection techniques able to learn online using only the feedback given by the chosen option (a.k.a. arm). We study a particular case of the rested and restless bandits in which the arms’ expected payoff is monotonically non-decreasing. This characteristic allows designing specifically crafted algorithms that exploit the regularity of the payoffs to provide tight regret bounds. We design an algorithm for the rested case (R-ed-UCB) and one for the restless case (R-less-UCB), providing a regret bound depending on the properties of the instance and, under certain circumstances, of $\widetilde{\mathcal{O}}(T^{\frac{2}{3}})$. We empirically compare our algorithms with state-of-the-art methods for non-stationary MABs over several synthetically generated tasks and an online model selection problem for a real-world dataset. Finally, using synthetic and real-world data, we illustrate the effectiveness of the proposed approaches compared with state-of-the-art algorithms for the non-stationary bandits.

Warehouse Management Systems have been evolving and improving thanks to new Data Intelligence techniques. However, many current optimizations have been applied to specific cases or are in great need of manual interaction. Here is where Reinforcement Learning techniques come into play, providing automatization and adaptability to current optimization policies. In this paper, we present Storehouse, a customizable environment that generalizes the definition of warehouse simulations for Reinforcement Learning. We also validate this environment against state-of-the-art reinforcement learning algorithms and compare these results to human and random policies.

In several real-world applications, a learner has access to multiple environment simulators, each with a different precision (e.g., simulation accuracy) and cost (e.g., computational time). In such a scenario, the learner faces the trade-off between selecting expensive accurate simulators or preferring cheap imprecise ones. We formalize this setting as a multi-fidelity variant of the stochastic best-arm identification problem, where querying the original arm is expensive, but multiple and biased approximations (i.e., fidelities) are available at lower costs. The learner's goal, in this setting, is to sequentially choose which simulator to query in order to minimize the total cost, while guaranteeing to identify the optimal arm with high probability. We first derive a lower bound on the identification cost, assuming that the maximum bias of each fidelity is known to the learner. Then, we propose a novel algorithm, Iterative Imprecise Successive Elimination (IISE), which provably reduces the total cost w.r.t. algorithms that ignore the multi-fidelity structure and whose cost complexity upper bound mimics the structure of the lower bound. Furthermore, we show that the cost complexity of IISE can be further reduced when the agent has access to a more fine-grained knowledge of the error introduced by the approximators.Finally, we numerically validate IISE, showing the benefits of our method in simulated domains.

Abstract We study the problem of identifying the policy space available to an agent in a learning process, having access to a set of demonstrations generated by the agent playing the optimal policy in the considered space. We introduce an approach based on frequentist statistical testing to identify the set of policy parameters that the agent can control, within a larger parametric policy space. After presenting two identification rules (combinatorial and simplified), applicable under different assumptions on the policy space, we provide a probabilistic analysis of the simplified one in the case of linear policies belonging to the exponential family. To improve the performance of our identification rules, we make use of the recently introduced framework of the Configurable Markov Decision Processes, exploiting the opportunity of configuring the environment to induce the agent to reveal which parameters it can control. Finally, we provide an empirical evaluation, on both discrete and continuous domains, to prove the effectiveness of our identification rules.

Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the policy space. The additional available information, compared to the standard bandit feedback, allows reusing samples generated by one policy to estimate the performance of other policies. Based on this observation, we propose an algorithm, RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST), for regret minimization in PO, that employs a randomized exploration strategy, differently from the existing optimistic approaches. When the policy space is finite, we show that under certain circumstances, it is possible to achieve constant regret, while always enjoying logarithmic regret. We also derive problem-dependent regret lower bounds. Then, we extend RANDOMIST to compact policy spaces. Finally, we provide numerical simulations on finite and compact policy spaces, in comparison with PO and bandit baselines.

The reward function is widely accepted as a succinct, robust, and transferable representation of a task. Typical approaches, at the basis of Inverse Reinforcement Learning (IRL), leverage on expert demonstrations to recover a reward function. In this paper, we study the theoretical properties of the class of reward functions that are compatible with the expert’s behavior. We analyze how the limited knowledge of the expert’s policy and of the environment affects the reward reconstruction phase. Then, we examine how the error propagates to the learned policy’s performance when transferring the reward function to a different environment. We employ these findings to devise a provably efficient active sampling approach, aware of the need for transferring the reward function, that can be paired with a large variety of IRL algorithms. Finally, we provide numerical simulations on benchmark environments.

Importance Sampling (IS) is a widely used building block for a large variety of off-policy estimation and learning algorithms. However, empirical and theoretical studies have progressively shown that vanilla IS leads to poor estimations whenever the behavioral and target policies are too dissimilar. In this paper, we analyze the theoretical properties of the IS estimator by deriving a novel anticoncentration bound that formalizes the intuition behind its undesired behavior. Then, we propose a new class of IS transformations, based on the notion of power mean. To the best of our knowledge, the resulting estimator is the first to achieve, under certain conditions, two key properties: (i) it displays a subgaussian concentration rate; (ii) it preserves the differentiability in the target distribution. Finally, we provide numerical simulations on both synthetic examples and contextual bandits, in comparison with off-policy evaluation and learning baselines.

The Configurable Markov Decision Process framework includes two entities: a Reinforcement Learning agent and a configurator that can modify some environmental parameters to improve the agent's performance. This presupposes that the two actors have the same reward functions. What if the configurator does not have the same intentions as the agent? This paper introduces the Non-Cooperative Configurable Markov Decision Process, a setting that allows having two (possibly different) reward functions for the configurator and the agent. Then, we consider an online learning problem, where the configurator has to find the best among a finite set of possible configurations. We propose two learning algorithms to minimize the configurator's expected regret, which exploits the problem's structure, depending on the agent's feedback. While a naive application of the UCB algorithm yields a regret that grows indefinitely over time, we show that our approach suffers only bounded regret. Furthermore, we empirically show the performance of our algorithm in simulated domains.

This paper presents a study of the policy improvement step that can be usefully exploited by approximate policy-iteration algorithms. When either the policy evaluation step or the policy improvement step returns an approximated result, the sequence of policies produced by policy iteration may not be monotonically increasing, and oscillations may occur. To address this issue, we consider safe policy improvements, i.e., at each iteration, we search for a policy that maximizes a lower bound to the policy improvement w.r.t. the current policy, until no improving policy can be found. We propose three safe policy-iteration schemas that differ in the way the next policy is chosen w.r.t. the estimated greedy policy. Besides being theoretically derived and discussed, the proposed algorithms are empirically evaluated and compared on some chain-walk domains, the prison domain, and on the Blackjack card game.

Abstract In real-world applications, inferring the intentions of expert agents (e.g., human operators) can be fundamental to understand how possibly conflicting objectives are managed, helping to interpret the demonstrated behavior. In this paper, we discuss how inverse reinforcement learning (IRL) can be employed to retrieve the reward function implicitly optimized by expert agents acting in real applications. Scaling IRL to real-world cases has proved challenging as typically only a fixed dataset of demonstrations is available and further interactions with the environment are not allowed. For this reason, we resort to a class of truly batch model-free IRL algorithms and we present three application scenarios: (1) the high-level decision-making problem in the highway driving scenario, and (2) inferring the user preferences in a social network (Twitter), and (3) the management of the water release in the Como Lake. For each of these scenarios, we provide formalization, experiments and a discussion to interpret the obtained results.

Traditional model-based reinforcement learning approaches learn a model of the environment dynamics without explicitly considering how it will be used by the agent. In the presence of misspecified model classes, this can lead to poor estimates, as some relevant available information is ignored. In this paper, we introduce a novel model-based policy search approach that exploits the knowledge of the current agent policy to learn an approximate transition model, focusing on the portions of the environment that are most relevant for policy improvement. We leverage a weighting scheme, derived from the minimization of the error on the model-based policy gradient estimator, in order to define a suitable objective function that is optimized for learning the approximate transition model. Then, we integrate this procedure into a batch policy improvement algorithm, named Gradient-Aware Model-based Policy Search (GAMPS), which iteratively learns a transition model and uses it, together with the collected trajectories, to compute the new policy parameters. Finally, we empirically validate GAMPS on benchmark domains analyzing and discussing its properties.

We consider Inverse Reinforcement Learning (IRL) about multiple intentions, \ie the problem of estimating the unknown reward functions optimized by a group of experts that demonstrate optimal behaviors. Most of the existing algorithms either require access to a model of the environment or need to repeatedly compute the optimal policies for the hypothesized rewards. However, these requirements are rarely met in real-world applications, in which interacting with the environment can be expensive or even dangerous. In this paper, we address the IRL about multiple intentions in a fully model-free and batch setting. We first cast the single IRL problem as a constrained likelihood maximization and then we use this formulation to cluster agents based on the likelihood of the assignment. In this way, we can efficiently solve, without interactions with the environment, both the IRL and the clustering problem. Finally, we evaluate the proposed methodology on simulated domains and on a real-world social-network application.

The choice of the control frequency of a system has a relevant impact on the ability of reinforcement learning algorithms to learn a highly performing policy. In this paper, we introduce the notion of action persistence that consists in the repetition of an action for a fixed number of decision steps, having the effect of modifying the control frequency. We start analyzing how action persistence affects the performance of the optimal policy, and then we present a novel algorithm, Persistent Fitted Q-Iteration (PFQI), that extends FQI, with the goal of learning the optimal value function at a given persistence. After having provided a theoretical study of PFQI and a heuristic approach to identify the optimal persistence, we present an experimental campaign on benchmark domains to show the advantages of action persistence and proving the effectiveness of our persistence selection method.

How can we effectively exploit the collected samples when solving a continuous control task with Reinforcement Learning? Recent results have empirically demonstrated that multiple policy optimization steps can be performed with the same batch by using off-distribution techniques based on importance sampling. However, when dealing with off-distribution optimization, it is essential to take into account the uncertainty introduced by the importance sampling process. In this paper, we propose and analyze a class of model-free, policy search algorithms that extend the recent Policy Optimization via Importance Sampling (Metelli et al., 2018) by incorporating two advanced variance reduction techniques: per-decision and multiple importance sampling. For both of them, we derive a high-probability bound, of independent interest, and then we show how to employ it to define a suitable surrogate objective function that can be used for both action-based and parameter-based settings. The resulting algorithms are finally evaluated on a set of continuous control tasks, using both linear and deep policies, and compared with modern policy optimization methods.

Configurable Markov Decision Processes (Conf-MDPs) have been recently introduced as an extension of the usual MDP model to account for the possibility of configuring the environment to improve the agent’s performance. Currently, there is still no suitable algorithm to solve the learning problem for real-world Conf-MDPs. In this paper, we fill this gap by proposing a trust-region method, Relative Entropy Model Policy Search (REMPS), able to learn both the policy and the MDP configuration in continuous domains without requiring the knowledge of the true model of the environment. After introducing our approach and providing a finite-sample analysis, we empirically evaluate REMPS on both benchmark and realistic environments by comparing our results with those of the gradient methods.

Policy Search (PS) is an effective approach to Reinforcement Learning (RL) for solving control tasks with continuous state-action spaces. In this paper, we address the exploration-exploitation trade-off in PS by proposing an approach based on Optimism in the Face of Uncertainty. We cast the PS problem as a suitable Multi Armed Bandit (MAB) problem, defined over the policy parameter space, and we propose a class of algorithms that effectively exploit the problem structure, by leveraging Multiple Importance Sampling to perform an off-policy estimation of the expected return. We show that the regret of the proposed approach is bounded by $\widetilde{\mathcal{O}}(\sqrt{T})$ for both discrete and continuous parameter spaces. Finally, we evaluate our algorithms on tasks of varying difficulty, comparing them with existing MAB and RL algorithms.

Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However, existing algorithms are mostly heuristic and do not offer any guarantee on the proposed solution. In this paper, we provide novel theoretical results showing that conditional mutual information naturally arises when bounding the ideal regression/classification errors achieved by different subsets of features. Leveraging on these insights, we propose a novel stopping condition for backward and forward greedy methods which ensures that the ideal prediction error using the selected feature subset remains bounded by a user-specified threshold. We provide numerical simulations to support our theoretical claims and compare to common heuristic methods.

How does the uncertainty of the value function propagate when performing temporal difference learning? In this paper, we address this question by proposing a Bayesian framework in which we employ approximate posterior distributions to model the uncertainty of the value function and Wasserstein barycenters to propagate it across state-action pairs. Leveraging on these tools, we present an algorithm, Wasserstein Q-Learning (WQL), starting in the tabular case and then, we show how it can be extended to deal with continuous domains. Furthermore, we prove that, under mild assumptions, a slight variation of WQL enjoys desirable theoretical properties in the tabular setting. Finally, we present an experimental campaign to show the effectiveness of WQL on finite problems, compared to several RL algorithms, some of which are specifically designed for exploration, along with some preliminary results on Atari games.

In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we propose a novel framework, Configurable Markov Decision Processes (Conf-MDPs), to model this new type of interaction with the environment. Furthermore, we provide a new learning algorithm, Safe Policy-Model Iteration (SPMI), to jointly and adaptively optimize the policy and the environment configuration. After having introduced our approach and derived some theoretical results, we present the experimental evaluation in two explicative problems to show the benefits of the environment configurability on the performance of the learned policy.

Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse. However, deciding when to stop optimizing and collect new trajectories is non-trivial, as it requires to account for the variance of the objective function estimate. In this paper, we propose a novel, model-free, policy search algorithm, POIS, applicable in both action-based and parameter-based settings. We first derive a high-confidence bound for importance sampling estimation; then we define a surrogate objective function, which is optimized offline whenever a new batch of trajectories is collected. Finally, the algorithm is tested on a selection of continuous control tasks, with both linear and deep policies, and compared with state-of-the-art policy optimization methods.

Inverse Reinforcement Learning (IRL) is an effective approach to recover a reward function that explains the behavior of an expert by observing a set of demonstrations. This paper is about a novel model-free IRL approach that, differently from most of the existing IRL algorithms, does not require to specify a function space where to search for the expert's reward function. Leveraging on the fact that the policy gradient needs to be zero for any optimal policy, the algorithm generates a set of basis functions that span the subspace of reward functions that make the policy gradient vanish. Within this subspace, using a second-order criterion, we search for the reward function that penalizes the most a deviation from the expert's policy. After introducing our approach for finite domains, we extend it to continuous ones. The proposed approach is empirically compared to other IRL methods both in the (finite) Taxi domain and in the (continuous) Linear Quadratic Gaussian (LQG) and Car on the Hill environments.