Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target distribution, which is impossible in online RL since we cannot sample from the optimal policy. Backpropagating policy gradient through the diffusion process incurs huge computational costs and instability, thus being expensive and not scalable. To enable efficient training of diffusion policies in online RL, we generalize the conventional denoising score matching by reweighting the loss function. The resulting Reweighted Score Matching (RSM) preserves the optimal solution and low computational cost of denoising score matching, while eliminating the need to sample from the target distribution and allowing learning to optimize value functions. We introduce two tractable reweighted loss functions to solve two commonly used policy optimization problems, policy mirror descent and max-entropy policy, resulting in two practical algorithms named Diffusion Policy Mirror Descent (DPMD) and Soft Diffusion Actor-Critic (SDAC). We conducted comprehensive comparisons on MuJoCo benchmarks. The empirical results show that the proposed algorithms outperform recent diffusion-policy online RLs on most tasks, and the DPMD improves more than 120% over soft actor-critic on Humanoid and Ant.

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations, derived from factorizations of the transition dynamics. We first theoretically justify that the optimal decision variable of offline IL lies in the representation space, significantly reducing the parameters to learn in the downstream IL. Moreover, the dynamics representations can be learned from arbitrary data collected with the same dynamics, allowing the reuse of massive non-expert data and mitigating the limited data issues. We present a tractable loss function inspired by noise contrastive estimation to learn the dynamics representations at the pre-training stage. Experiments on MuJoCo demonstrate that our proposed algorithm can mimic expert policies with as few as a single trajectory. Experiments on real quadrupeds show that we can leverage pre-trained dynamics representations from simulator data to learn to walk from a few real-world demonstrations.

Reinforcement learning (RL) for collaborative agents capable of cooperating with humans to accomplish tasks has long been a central goal in the RL community. While prior approaches have made progress in adapting collaborative agents to diverse human partners, they often focus solely on optimizing task performance and overlook human preferences—despite the fact that such preferences often diverge from the reward-maximization objective of the environment. Addressing this discrepancy poses significant challenges: humans typically provide only a small amount of offline, preference-related feedback and are unable to engage in online interactions, resulting in a distributional mismatch between the agent’s online learning process and the offline human data. To tackle this, we formulate the problem as an online&offline reinforcement learning problem that jointly integrates online generalization and offline preference learning, entirely under an offline training regime. We propose a simple yet effective training framework built upon existing RL algorithms that alternates between offline preference learning and online generalization recovery, ensuring the stability and alignment of both learning objectives. We evaluate our approach on a benchmark built upon the Overcooked environment—a standard environment for human-agent collaboration—and demonstrate remarkable performance across diverse preference styles and cooperative scenarios.

We focus on learning the zero-constraint-violation safe policy in model-free reinforcement learning (RL). Existing model-free RL studies mostly use the posterior penalty to penalize dangerous actions, which means they must experience the danger to learn from the danger. Therefore, they cannot learn a zero-violation safe policy even after convergence. To handle this problem, we leverage the safety-oriented energy functions to learn zero-constraint-violation safe policies and propose the safe set actor-critic (SSAC) algorithm. The energy function is designed to increase rapidly for potentially dangerous actions, locating the safe set on the action space. Therefore, we can identify the dangerous actions prior to taking them and achieve zero-constraint violation. Our major contributions are twofold. First, we use the data-driven methods to learn the energy function, which releases the requirement of known dynamics. Second, we formulate a constrained RL problem to solve the zero-violation policies. We prove that our Lagrangian-based constrained RL solutions converge to the constrained optimal zero-violation policies theoretically. The proposed algorithm is evaluated on the complex simulation environments and a hardware-in-loop (HIL) experiment with a real autonomous vehicle controller. Experimental results suggest that the converged policies in all environments achieve zero-constraint violation and comparable performance with model-based baseline.

Safety certificates based on energy functions can provide demonstrable safety for complex robotic systems. However, all recent studies on learning-based energy function synthesis only consider the feasibility of the control policy, which might cause over-conservativeness and even fail to achieve the control goal. To solve the problem of over-conservative controllers, we proposed the magnitude regularization technique to improve the controller performance of safe controllers by reducing the conservativeness inside the energy function, while keeping the promising provable safety guarantees. Specifically, we quantify the conservativeness by the magnitude of the energy function, and we reduce the conservativeness by adding a magnitude regularization term to the synthesis loss. We propose an algorithm using reinforcement learning (RL) for synthesis to unify the learning process of safe controllers and energy functions. We conducted simulation experiments on Safety Gym and real-robot experiments using small quadrotors. Simulation results show that the proposed algorithm does reduce the conservativeness of the energy function and outperforms baselines in terms of controller performance while maintaining safety. Real-robot experiments have shown that the proposed algorithm indeed reduce conservativeness on the small quadrotors.

We study sim-to-real skill transfer and discovery in the context of robotics control using representation learning. We draw inspiration from spectral decomposition of Markov decision processes. The spectral decomposition brings about representation that can linearly represent the state-action value function induced by any policies, thus can be regarded as skills. The skill representations are transferable across arbitrary tasks with the same transition dynamics. Moreover, to handle the sim-to-real gap in the dynamics, we propose a skill discovery algorithm that learns new skills caused by the sim-to-real gap from real-world data. We promote the discovery of new skills by enforcing orthogonal constraints between the skills to learn and the skills from simulators, and then synthesize the policy using the enlarged skill sets. We demonstrate our methodology by transferring quadrotor controllers from simulators to Crazyflie 2.1 quadrotors. We show that we can learn the skill representations from a single simulator task and transfer these to multiple different real-world tasks including hovering, taking off, landing and trajectory tracking. Our skill discovery approach helps narrow the sim-to-real gap and improve the real-world controller performance by up to 30.2%.

Safe reinforcement learning (RL) that solves constraint-satisfactory policies provides a promising way to the broader safety-critical applications of RL in real-world problems such as robotics. Among all safe RL approaches, model-based methods reduce training time violations further due to their high sample efficiency. However, lacking safety robustness against the model uncertainties remains an issue in safe model-based RL, especially in training time safety. In this paper, we propose a distributional reachability certificate (DRC) and its Bellman equation to address model uncertainties and characterize robust persistently safe states. Furthermore, we build a safe RL framework to resolve constraints required by the DRC and its corresponding shield policy. We also devise a line search method to maintain safety and reach higher returns simultaneously while leveraging the shield policy. Comprehensive experiments on classical benchmarks such as constrained tracking and navigation indicate that the proposed algorithm achieves comparable returns with much fewer constraint violations during training. Our code is available at https://github.com/ManUtdMoon/Distributional-Reachability-Policy-Optimization.Note to Practitioners—Although it has been proven that RL can be applied in complex robotics control tasks, the training process of an RL control policy induces frequent failures because the agent needs to learn safety through constraint violations. This issue hinders the promotion of RL because a large amount of failure of robots is too expensive to afford. This paper aims to reduce the training-time violations of RL-based control methods, enabling RL to be leveraged in a broader application area. To achieve the goal, we first introduce a safety quantity describing the distribution of potential constraint violations in the long term. By imposing constraints on the quantile of the safety distribution, we can realize safety robust to the model uncertainty, which is necessary for real-world robot learning with environment uncertainty. Second, we further devise a shield policy aiming to minimize the constraint violation. The policy will intervene when the agent is about to violate state constraints, further enhancing exploration safety. Third, we implement a line search method to find an action pursuing near-optimal performance when fulfilling safety requirements strictly. Our experimental results indicate that the proposed algorithm reduces training-time violations significantly while maintaining competitive task performance. We make a step towards applying RL safely in real-world tasks. Our future work includes conducting physical verification on real robots to evaluate the algorithm and improving safety further by starting from an initially safe control policy that comes from domain knowledge.

We study the multi-agent Bayesian optimization (BO) problem, where multiple agents maximize a black-box function via iterative queries. We focus on Entropy Search (ES), a sample-efficient BO algorithm that selects queries to maximize the mutual information about the maximum of the black-box function. One of the main challenges of ES is that calculating the mutual information requires computationallycostly approximation techniques. For multi-agent BO problems, the computational cost of ES is exponential in the number of agents. To address this challenge, we propose the Gaussian Max-value Entropy Search, a multi-agent BO algorithm with favorable sample and computational efficiency. The key to our idea is to use a normal distribution to approximate the function maximum and calculate its mutual information accordingly. The resulting approximation allows queries to be cast as the solution of a closed-form optimization problem which, in turn, can be solved via a modified gradient ascent algorithm and scaled to a large number of agents. We demonstrate the effectiveness of Gaussian max-value Entropy Search through numerical experiments on standard test functions and real-robot experiments on the source seeking problem. Results show that the proposed algorithm outperforms the multi-agent BO baselines in the numerical experiments and can stably seek the source with a limited number of noisy observations on real robots.

Decision and control are core functionalities of high-level automated vehicles. Current mainstream methods, such as functional decomposition and end-to-end reinforcement learning (RL), suffer high time complexity or poor interpretability and adaptability on real-world autonomous driving tasks. In this article, we present an interpretable and computationally efficient framework called integrated decision and control (IDC) for automated vehicles, which decomposes the driving task into static path planning and dynamic optimal tracking that are structured hierarchically. First, the static path planning generates several candidate paths only considering static traffic elements. Then, the dynamic optimal tracking is designed to track the optimal path while considering the dynamic obstacles. To that end, we formulate a constrained optimal control problem (OCP) for each candidate path, optimize them separately, and follow the one with the best tracking performance. To unload the heavy online computation, we propose a model-based RL algorithm that can be served as an approximate-constrained OCP solver. Specifically, the OCPs for all paths are considered together to construct a single complete RL problem and then solved offline in the form of value and policy networks for real-time online path selecting and tracking, respectively. We verify our framework in both simulations and the real world. Results show that compared with baseline methods, IDC has an order of magnitude higher online computing efficiency, as well as better driving performance, including traffic efficiency and safety. In addition, it yields great interpretability and adaptability among different driving scenarios and tasks.

Reinforcement learning (RL) has shown excellent performance in the sequential decision-making problem, where safety in the form of state constraints is of great significance in the design and application of RL. Simple constrained end-to-end RL methods might lead to significant failure in a complex system like autonomous vehicles. In contrast, some hierarchical RL (HRL) methods generate driving goals directly, which could be closely combined with motion planning. With safety requirements, some safe-enhanced RL methods add post-processing modules to avoid unsafe goals or achieve expectation-based safety, which accepts the existence of unsafe states and allows some violations of safe constraints. However, ensuring state safety is vital for autonomous vehicles. Therefore, this paper proposes a state-based safety enhancement method for autonomous driving via direct hierarchical reinforcement learning. Finally, we design a constrained reinforcement learner based on the State-based Constrained Markov Decision Process (SCMDP), where a learnable safety module could adjust the constraint strength adaptively. We integrate a dynamic module in the policy training and generate future goals considering safety, temporal-spatial continuity, and dynamic feasibility, which could eliminate dependence on the prior model. Simulations in the typical highway scenes with uncertainties show that the proposed method has better training performance, higher driving safety in interactive scenes, more decision intelligence in traffic congestions, and better economic driving ability on roads with changing slopes.

In the area of autonomous driving, it typically brings great difficulty in solving the motion planning problem since the vehicle model is nonlinear and the driving scenarios are complex. Particularly, most of the existing methods cannot be generalized to dynamically changing scenarios with varying surrounding vehicles. To address this problem, this development here investigates the framework of integrated decision and control. As part of the modules, static path planning determines the reference candidates ahead, and then the optimal path-tracking controller realizes the specific autonomous driving task. An innovative and effective constrained finite-horizon approximate dynamic programming (ADP) algorithm is herein presented to generate the desired control policy for effective path tracking. With the generalized policy neural network that maps from the state to the control input, the proposed algorithm preserves the high effectiveness for the motion planning problem towards changing driving environments with varying surrounding vehicles. Moreover, the algorithm attains the noteworthy advantage of alleviating the typically heavy computational loads with the mode of offline training and online execution. As a result of the utilization of multi-layer neural networks in conjunction with the actor-critic framework, the constrained ADP method is capable of handling complex and multidimensional scenarios. Finally, various simulations have been carried out to show that the constrained ADP algorithm is effective.

The Hamilton-Jacobi-Bellman (HJB) equation serves as the necessary and sufficient condition for the optimal solution to the continuous-time (CT) optimal control problem (OCP). Compared with the infinite-horizon HJB equation, the solving of the finite-horizon (FH) HJB equation has been a long-standing challenge, because the partial time derivative of the value function is involved as an additional unknown term. To address this problem, this study first-time bridges the link between the partial time derivative and the terminal-time utility function, and thus it facilitates the use of the policy iteration (PI) technique to solve the CT FH OCPs. Based on this key finding, the FH approximate dynamic programming (ADP) algorithm is proposed leveraging an actor-critic framework. It is shown that the algorithm exhibits important properties in terms of convergence and optimality. Rather importantly, with the use of multilayer neural networks (NNs) in the actor-critic architecture, the algorithm is suitable for CT FH OCPs toward more general nonlinear and complex systems. Finally, the effectiveness of the proposed algorithm is demonstrated by conducting a series of simulations on both a linear quadratic regulator (LQR) problem and a nonlinear vehicle tracking problem.

Constrained reinforcement learning (CRL) has gained significant interest recently, since safety constraints satisfaction is critical for real-world problems. However, existing CRL methods constraining discounted cumulative costs generally lack rigorous definition and guarantee of safety. In contrast, in the safe control research, safety is defined as persistently satisfying certain state constraints. Such persistent safety is possible only on a subset of the state space, called feasible set, where an optimal largest feasible set exists for a given environment. Recent studies incorporate feasible sets into CRL with energy-based methods such as control barrier function (CBF), safety index (SI), and leverage prior conservative estimations of feasible sets, which harms the performance of the learned policy. To deal with this problem, this paper proposes the reachability CRL (RCRL) method by using reachability analysis to establish the novel self-consistency condition and characterize the feasible sets. The feasible sets are represented by the safety value function, which is used as the constraint in CRL. We use the multi-time scale stochastic approximation theory to prove that the proposed algorithm converges to a local optimum, where the largest feasible set can be guaranteed. Empirical results on different benchmarks validate the learned feasible set, the policy performance, and constraint satisfaction of RCRL, compared to CRL and safe control baselines.

Model information can be used to predict future trajectories, so it has huge potential to avoid dangerous regions when applying reinforcement learning (RL) on real-world tasks, like autonomous driving. However, existing studies mostly use model-free constrained RL, which causes inevitable constraint violations. This paper proposes a model-based feasibility enhancement technique of constrained RL, which enhances the feasibility of policy using generalized control barrier function (GCBF) defined on the distance to constraint boundary. By using the model information, the policy can be optimized safely without violating actual safety constraints, and the sample efficiency is increased. The infeasibility in solving the constrained policy gradient is handled by an adaptive coefficient mechanism. We evaluate the proposed method in both simulations and real vehicle experiments in a complex autonomous driving collision avoidance task. The proposed method achieves up to four times fewer constraint violations and converges 3.36 times faster than baseline constrained RL approaches.