Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Reinforcement learning studies how an agent can choose actions over time to earn rewards, using experience to improve its decisions. Common approaches include value-based methods such as Q-learning, policy-gradient methods such as PPO, and model-based methods that learn or use a model of the environment; offline and hierarchical methods address learning from fixed data and long tasks. Applications range from Atari and MuJoCo benchmarks to robot control, traffic, games, and language-model agents that use tools or solve multi-step problems. A central challenge is making learning efficient and reliable when rewards are sparse or imperfect, environments change, and success in simulation or benchmarks may not transfer safely to deployment.

Latest papers

1,742 papers237 papers in the last four weeks, up 46% on the four weeks before. 1.4% of all new papers.

Apr 2, 2025

A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown Lévy Process Dynamics

This paper develops a model-based framework for continuous-time policy evaluation (CTPE) in reinforcement learning, incorporating both Brownian and Lévy noise to model stochastic dynamics influenced by rare and extreme events. Our approach formulates the policy evaluation problem as solving a partial integro-differential equation (PIDE) for the value function with unknown coefficients. A key challenge in this setting is accurately recovering the unknown coefficients in the stochastic dynamics, particularly when driven by Lévy processes with heavy tail effects. To address this, we propose a robust numerical approach that effectively handles both unbiased and censored trajectory datasets. This method combines maximum likelihood estimation with an iterative tail correction mechanism, improving the stability and accuracy of coefficient recovery. Additionally, we establish a theoretical bound for the policy evaluation error based on coefficient recovery error. Through numerical experiments, including a real-data BTC price experiment, we demonstrate the effectiveness and robustness of our method in recovering heavy-tailed Lévy dynamics and verify the theoretical error analysis in policy evaluation.

Qihao Ye, Xiaochuan Tian, Yuhua Zhu

Reinforcement Learning Value Function Estimation Robust RL Model-Based RL

Mar 20, 2025

CONTHER: Context-Aware Reinforcement Learning for Robotic Manipulation with Sparse Rewards

This paper investigates whether sequential context improves goal-conditioned Reinforcement Learning in sparse-reward manipulation tasks. While Hindsight Experience Replay (HER) addresses reward sparsity through goal relabeling, its operation on isolated transitions limits its ability to capture temporal dependencies inherent in joint-space control. We hypothesize that incorporating motion history can enhance policy learning and introduce CONTHER, which integrates a Transformer-based architecture with a modified HER replay buffer. The Transformer encodes sequences of prior states and goals to provide temporal awareness, while the buffer populates experience with artificially successful trajectories. Two architectural variants are analyzed to examine how contextual information should be integrated. In simulated point-reaching tasks with a UR3 manipulator, CONTHER achieves a 38.46% higher average success rate compared to baselines and outperforms the strongest baseline by 28.21%, with faster convergence and more stable learning. The framework is further evaluated on three dynamic tasks requiring complex trajectory following and obstacle avoidance, where temporal context is critical. By operating directly on joint velocities, the approach provides a foundation for transfer to physical systems. The primary contribution is a systematic investigation into fusing sequential context with goal relabeling, offering insights into how temporal awareness benefits policy learning.

Maria Makarova, Qian Liu, Dzmitry Tsetserukou

Intelligent Space Robotics Laboratory, Center for Digital Engineering, Skolkovo Institute of Science and Technology (Skoltech), 121205 Moscow, Russia · Department of Computer Science and Technology, Dalian University of Technology, China

Reinforcement Learning Experience Replay Robotic RL Sparse-Reward RL Goal-Conditioned RL Hindsight Experience Replay

Mar 19, 2025

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we study building blocks for self-supervised RL that unlock substantial improvements in scalability, with network depth serving as a critical factor. Whereas most RL papers in recent years have relied on shallow architectures (around 2 - 5 layers), we demonstrate that increasing the depth up to 1024 layers can significantly boost performance. Our experiments are conducted in an unsupervised goal-conditioned setting, where no demonstrations or rewards are provided, so an agent must explore (from scratch) and learn how to maximize the likelihood of reaching commanded goals. Evaluated on simulated locomotion and manipulation tasks, our approach increases performance on the self-supervised contrastive RL algorithm by

2\times

-

50\times

, outperforming other goal-conditioned baselines. Increasing the model depth not only increases success rates but also qualitatively changes the behaviors learned. The project webpage and code can be found here: https://wang-kevin3290.github.io/scaling-crl/.

Kevin Wang, Ishaan Javali, Michał Bortkiewicz +2

Princeton University · Warsaw University of Technology · Warsaw University of Technology, Tooploox, IDEAS Research Institute

Reinforcement Learning Self-Supervised RL Robotic RL Contrastive RL Goal-Conditioned RL

Feb 25, 2025

Supervised Reward Inference

Existing approaches to reward inference typically assume that humans provide demonstrations according to specific behavior models. However, humans often indicate their goals through a wide range of behaviors, from actions that are suboptimal due to poor planning or execution to behaviors intended to communicate goals rather than achieve them. One existing solution for inferring rewards from such behavior

\unicode{x2013}

provided it is drawn from the same distribution at training and deployment

\unicode{x2013}

is to construct a dataset of behavior paired with known rewards, and to learn the mapping from behavior to rewards; however, prior methods in this family face notable limitations, such as restrictions to tabular settings. Given such a dataset, we propose instead that supervised learning offers a parsimonious yet powerful solution, which we term Supervised Reward Inference (SRI). Theoretically, we prove that SRI is asymptotically Bayes-optimal under standard assumptions. Empirically, SRI achieves near-ceiling performance on a prior benchmark for reward inference from suboptimal behavior, while on Meta-World robotics tasks, it infers rewards from even arbitrarily suboptimal demonstrations as accurately as those demonstrations allow. Finally, we demonstrate our framework's universality with straightforward generalizations to action- and goal-prediction.

Will Schwarzer, Jordan Schneider, Philip S. Thomas +1

University of Massachusetts · Anthropic · Work done while at the University of Texas.

Reward Modeling Reinforcement Learning Learning from Suboptimal Demonstrations

Feb 19, 2025

Safe Learning Under Irreversible Dynamics via Asking for Help

Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu +1

Division of Computer Science University of California Berkeley, CA 94720-1776, USA

Regret Minimization in RL Reinforcement Learning Safe RL

Feb 17, 2025

Does Knowledge About Perceptual Uncertainty Help an Agent in Automated Driving?

Agents in real-world scenarios like automated driving deal with uncertainty in their environment, in particular due to perceptual uncertainty. Although, reinforcement learning is dedicated to autonomous decision-making under uncertainty these algorithms are typically not informed about the uncertainty currently contained in their environment. On the other hand, uncertainty estimation for perception itself is typically directly evaluated in the perception domain, e.g., in terms of false positive detection rates or calibration errors based on camera images. Its use for deciding on goal-oriented actions remains largely unstudied. In this paper, we investigate how an agent's behavior is influenced by an uncertain perception and how this behavior changes if information about this uncertainty is available. Therefore, we consider a proxy task, where the agent is rewarded for driving a route as fast as possible without colliding with other road users. For controlled experiments, we introduce uncertainty in the observation space by perturbing the perception of the given agent while informing the latter. Our experiments show that an unreliable observation space modeled by a perturbed perception leads to a defensive driving behavior of the agent. Furthermore, when adding the information about the current uncertainty directly to the observation space, the agent adapts to the specific situation and in general accomplishes its task faster while, at the same time, accounting for risks.

Natalie Grabowsky, Annika Mütze, Joshua Wendland +2

Institute of Mathematics Technical University of Berlin Berlin, Germany · Department of Mathematics University of Wuppertal Wuppertal, Germany · Faculty of Computer Science Ruhr University Bochum Bochum, Germany

Autonomous Driving Planning RL for Autonomous Driving Reinforcement Learning

Feb 2, 2025

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning

Deep reinforcement learning (DRL) has successfully addressed many complex control problems. However, the neural networks representing policies or values remain opaque, undermining trust in high-stakes applications. While concept-based methods have shown promise in deciphering internal representations in computer vision, applying them to DRL is impeded by the absence of pre-defined semantic concepts in continuous state spaces. In this work, we propose a novel concept-based explanation framework designed to provide fine-grained, neuron-level insights into DRL models. Unlike previous approaches that rely on manual feature engineering, our framework automatically aligns neuron activations with logical formulas composed of semantic predicates. To bridge the gap between continuous signals and symbolic reasoning, we introduce a value-sensitive discretization mechanism that transforms raw state features into interpretable atomic concepts. This ensures that the vocabulary used for explanation captures strategic decision boundaries relevant to the agent's value assessment. By composing these interpretable concepts and matching them with neuron behaviors, we derive explicit explanations for the network's internal representations. Experimental results on both continuous and discrete environments demonstrate that our method effectively identifies meaningful decision-making patterns, offering faithful explanations that align with human intuition.

Zeyu Jiang, Hai Huang, Xingquan Zuo

School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China

Reinforcement Learning Concept-Based Explanations Neural Network Interpretability

Dec 6, 2024

Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agents

Reinforcement learning (RL) has demonstrated remarkable capabilities in training agents to solve complex tasks autonomously, such as mobile robots, UAVs/UGVs, and game-playing agents). However, scaling RL to master multiple tasks simultaneously (i.e., so-called multi-task RL) remains a significant challenge. Such a multi-task RL capability especially is important for agents to adapt to changes in real-world operational environments. State-of-the-art works show that, training agents with neural networks and shared structures across tasks promises improved generalization in simultaneous multi-task RL. However, they still suffer from task interference and incur high energy consumption due to intensive computation. To address this, we propose MTSpark, a novel methodology that enables energy-efficient simultaneous multi-task RL using spiking neural networks (SNNs) equipped with active dendrites for bio-inspired generalist agents. Specifically, MTSpark enhances a Deep Spiking Q-Network (DSQN) with active dendrites, a dueling structure, and task-specific context signals to dynamically form specialized sub-networks for individual tasks, while exploiting sparse operations for energy-efficient network processing. Experimental results demonstrate that MTSpark achieves higher performance and efficiency compared to state-of-the-art by obtaining high scores across three Atari games (i.e., Pong: -5.4, Breakout: 0.6, and Enduro: 371.2), approaching human-level performance (i.e., Pong: -3, Breakout: 31, Enduro: 368), while incurring similar memory and about 2x lower energy than state-of-the-art. These results show that our MTSpark potentially advances the frontiers toward energy-efficient generalist agents by combining RL and SNNs.

Rachmad Vidya Wicaksana Putra, Avaneesh Devkota, Muhammad Shafique

eBRAIN Lab · New York University (NYU) Abu Dhabi

Reinforcement Learning Deep Q-Learning Spiking Neural Networks Multi-Task RL

Dec 5, 2024

ELEMENT: Episodic and Lifelong Exploration via Maximum Entropy

Reinforcement learning agents depend on reward signals whose density is rarely under the designer's control, and when such signals are absent, an agent must generate its own drive to explore. State entropy maximization offers a principled objective for this, but existing methods break down at scale in two ways: the intrinsic reward vanishes once a state has been visited, discouraging revisits to the very gateways that lead onward, and estimating entropy over millions of accumulated observations becomes computationally prohibitive. We address both with Episodic and Lifelong Exploration via Maximum Entropy (ELEMENT), a multiscale intrinsically motivated framework for reward-free exploration that transfers to downstream tasks. ELEMENT couples lifelong entropy maximization with a complementary episodic term acting on a faster timescale. For the episodic term, we derive average episodic state entropy, an intrinsic reward that is the exact minimizer of a tractable upper bound on the reward-decomposition objective; for the lifelong term, we propose a

k

NN graph-based estimator that keeps entropy tractable without forgetting. ELEMENT consistently outperforms state-of-the-art intrinsic reward baselines on state coverage and unsupervised pre-training. Videos, code, and supplementary material: https://sites.google.com/view/element-rl.

Hongming Li, Zhao Yang, Xiaoxuan Liang +2

Zhejiang Lab, Huangzhou, China · Vrije Universiteit Amsterdam, Amsterdam, the Netherlands · Computational NeuroEngineering Laboratory at the University of Florida, Gainesville, USA

Reward-Free RL Reinforcement Learning Intrinsic Motivation Intrinsic Reward Methods RL Exploration Maximum Entropy RL+1

Nov 14, 2024

Temporal difference learning adapts to incomplete coverage: an oracle inequality over subgraphs

Temporal difference (TD) and Monte Carlo (MC) are two fundamental principles for value function estimation in reinforcement learning. TD is asymptotically efficient for value estimation, whereas MC requires only adequate target visitation. We show that these advantages are automatically combined by ordinary TD in the tabular setting. We identify the subgraph Bellman variance, arising from bootstrapping within a subgraph and rollouts outside it, as a fundamental quantity connecting the MC and efficient TD benchmarks. With independent trajectories, we prove a non-asymptotic oracle inequality: the mean squared error of full TD is bounded by this variance divided by the sample size for every sufficiently covered subgraph containing the target, up to a higher-order remainder whose occupancy dependence is confined to that subgraph. No subgraph is supplied to the algorithm. TD thus adapts without selecting a subgraph or requiring global coverage. A finite-sample minimax lower bound shows that the asymptotic variance of TD need not be attainable before rare states are adequately observed. Experimental studies examine the transition between these variance scales and its dependence on visitation structure.

Wenlong Mou, Jian Qian

Department of Statistical Sciences, University of Toronto · Department of EECS, Massachusetts Institute of Technology

Temporal-Difference Learning Reinforcement Learning Value Function Estimation

Nov 10, 2024

Reinforcement learning for Quantum Tiq-Taq-Toe

Quantum Tiq-Taq-Toe is a well-known benchmark and playground for both quantum computing and machine learning. Despite its popularity, no reinforcement learning (RL) methods have been applied to Quantum Tiq-Taq-Toe. Although there has been some research on Quantum Chess this game is significantly more complex in terms of computation and analysis. Therefore, we study the combination of quantum computing and reinforcement learning in Quantum Tiq-Taq-Toe, which may serve as an accessible testbed for the integration of both fields. Quantum games are challenging to represent classically due to their inherent partial observability and the potential for exponential state complexity. In Quantum Tiq-Taq-Toe, states are observed through Measurement (a 3x3 matrix of state probabilities) and Move History (a 9x9 matrix of entanglement relations), making strategy complex as each move can collapse the quantum state.

Catalin-Viorel Dinu, Thomas Moerland

Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands

Reinforcement Learning Game-Playing Agents

Oct 31, 2024

RL-STaR: Theoretical Analysis of Reinforcement Learning Frameworks for Self-Taught Reasoner

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is often scarce. The self-taught reasoner (STaR) framework addresses this by using reinforcement learning to automatically generate reasoning steps, reducing reliance on human-labeled data. Although STaR and its variants have demonstrated empirical success, a theoretical foundation explaining these improvements is lacking. This work provides a theoretical framework for understanding the effectiveness of reinforcement learning on CoT reasoning and STaR. Our contributions are: (1) criteria for the quality of pre-trained models necessary to initiate effective reasoning improvement; (2) an analysis of policy improvement, showing why LLM reasoning improves iteratively with STaR; (3) conditions for convergence to an optimal reasoning policy; and (4) an examination of STaR's robustness, explaining how it can improve reasoning even when incorporating occasional incorrect steps. We also run RL-STaR on GPT-2, Qwen2.5-0.5B and Phi-3-mini, and the measured return curves follow the ones the analysis predicts. This framework bridges empirical findings with theoretical insights, advancing reinforcement learning approaches for reasoning in LLMs.

Fu-Chieh Chang, Yu-Ting Lee, Hui-Ying Shih +2

MediaTek Research, Taipei, Taiwan · Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan · Department of Mathematical Sciences, National Chengchi University, Taipei, Taiwan +2

Reinforcement Learning RL for Language Model Reasoning Language Model Self-Improvement LLM Reasoning

Oct 18, 2024

Streaming Deep Reinforcement Learning Finally Works

Learning from a stream of experience as it arrives, also known as streaming learning, is a core part of natural learning. However, reliable streaming learning has remained a persistent challenge in modern deep reinforcement learning (RL). Instead, most deep RL algorithms learn from old experience by storing past interactions in a buffer. We show that both classical streaming RL, such as Q-learning and actor-critic, when used with deep neural networks, and batch deep RL, such as PPO, SAC, and DQN, when adapted to the streaming setting, often fail to learn. Across 58 Atari games and 50 continuous-control tasks, we find that these methods, in aggregate, perform close to random policies despite extensive task-specific hyperparameter searches. We call this pattern stream barrier. Here, we introduce Stream-X, a shared recipe for streaming deep RL algorithms that combines signal normalization, representation stabilization, and controlled parameter updates. By applying Stream-X to several base streaming RL algorithms, we provide the first family of deep RL algorithms to overcome the stream barrier. Using one prescribed hyperparameter configuration per algorithm across tasks, Stream-X substantially improves aggregate performance, often on par with batch RL algorithms. Beyond these benchmarks, we demonstrate learning with Stream-X algorithms under nonstationarity and resource constraints. Stream-AC, one of the Stream-X algorithms, repeatedly recovers performance across alternating floor-friction regimes in simulation, outperforming the evaluated PPO and SAC baselines. It also learns a heading tracking task on a robot using proprioceptive and visual features from the on-board camera in a naturally changing laboratory environment. Stream-Q learns a Pong game from pixels directly on an ESP32-S3 microcontroller, a device with limited compute and memory.

Mohamed Elsayed, Elena Sorina Lupu, Gautham Vasan +1

Department of Computing Science, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii) · Canada CIFAR AI Chair

Reinforcement Learning Actor-Critic Methods Policy Learning Streaming Algorithms

Oct 4, 2024

Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (CMDP), agents train on a fixed, finite set of contexts and must generalize to new ones. Recent work has demonstrated that training on additional states, even if they are irrelevant for solving the current context, can improve generalization to unseen contexts. In this paper, we demonstrate that training on these states can indeed improve generalization, but can come at a cost of reducing the accuracy of the learned value function, which should hurt generalization. We hypothesize and demonstrate that increasing the agent's coverage by training on these additional states while also increasing the accuracy improves generalization even further. Inspired by this, we propose a simple approach Explore-Go that leverages existing pure exploration strategies in a new way: by introducing a pure exploration phase at the start of each training episode. Unlike previous approaches that apply exploration strategies for the purpose of improving generalization, our approach can be combined with both on- and off-policy algorithms. We demonstrate the effectiveness of Explore-Go when combined with several popular algorithms and show an increase in test-time performance across several generalization benchmarks, even partially observable ones. With this, we hope to provide practitioners with a simple modification that can significantly improve the generalization of their agents.

Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1

Delft University of Technology, Delft, The Netherlands

Reinforcement Learning RL Exploration Transfer Learning Contextual RL Zero-Shot Policy Transfer Policy Learning+2

Oct 3, 2024

Deep Reinforcement Learning for Reach-Avoid-Stay Problems

Reach-Avoid-Stay (RAS) tasks are essential in applications where systems must safely reach a target set and remain within it under all bounded disturbances. Existing approaches either struggle to compute the maximal robust RAS set, the set of all states from which the RAS task is achievable, or are limited in handling general dynamic systems. To address these challenges, this paper proposes a two-step deep reinforcement learning framework that jointly learns the maximal robust RAS set and the corresponding control policy. The first step identifies the maximal robust control-invariant set within the target set and derives a policy that ensures the system remains within it. The second step computes the maximal robust reach-avoid (RA) set using this invariant set as the target, and it is proven that this RA set is equivalent to the maximal robust RAS set. Leveraging this result, a switching policy is constructed from the two step-wise policies, which constitutes a valid policy guaranteeing completion of the RAS task. Simulation results demonstrate that the proposed framework (1) computes the exact maximal robust RAS set in the absence of training errors, yielding the least restrictive RAS policy, and (2) identifies the RAS set with high accuracy while outperforming baseline methods on RAS tasks.

Gabriel Chenevert, Jingqi Li, Achyuta kannan +2

Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, USA · Department of Aerospace Engineering and Engineering Mechanics, at University of Texas, Austin, USA · Department of Computer Science, North Carolina State University, Raleigh, USA +1

Robust Control Reinforcement Learning

Sep 22, 2024

Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning

We study a structured class of Markov Decision Processes, known as Exo-MDPs, in which the state space is partitioned into exogenous and endogenous components. Exogenous states evolve stochastically, independent of the agent's actions, while endogenous states evolve deterministically based on both state components and actions. Exo-MDPs capture many operations research settings, including inventory control, resource management, and ride-sharing. Our first contribution is structural: we establish a representational equivalence between discrete MDPs, Exo-MDPs, and discrete linear mixture MDPs. Our second contribution is statistical. We characterize the minimax regret of learning in Exo-MDPs when the effective dimension r is small relative to the endogenous state and action spaces. When the exogenous states are unobserved, we prove matching upper and lower regret bounds of order

Θ(Hr \sqrt{K})

over

K

episodes of horizon

H

, where

r

is the effective dimension of the Exo-MDP. When exogenous states are observed, the minimax regret improves to

Θ(H\sqrt{ r K})

, revealing a

Θ(\sqrt{r})

statistical gap due to observation of the exogenous states. These results show that Exo-MDPs decouple sample complexity from action space and endogenous state space. We validate these insights with experiments on inventory control and resource allocation.

Jia Wan, Sean R. Sinclair, Devavrat Shah +1

Laboratory for Information and Decision Systems, Massachusetts Institute of Technology · Department of Industrial Engineering and Management Sciences, Northwestern University

Regret Minimization in RL Markov Decision Processes Reinforcement Learning Markov Models Sample-Efficient RL

Aug 19, 2024

Mitigating the Stability-Plasticity Dilemma in Adaptive Train Scheduling with Curriculum-Driven Continual DQN Expansion

A continual learning agent builds on previous experiences to develop increasingly complex behaviors by adapting to non-stationary and dynamic environments while preserving previously acquired knowledge. However, scaling these systems presents significant challenges, particularly in balancing the preservation of previous policies with the adaptation of new ones to current environments. This balance, known as the stability-plasticity dilemma, is especially pronounced in complex multi-agent domains such as the train scheduling problem, where environmental and agent behaviors are constantly changing, and the search space is vast. In this work, we propose addressing these challenges in the train scheduling problem using curriculum learning. We design a curriculum with adjacent skills that build on each other to improve generalization performance. Introducing a curriculum with distinct tasks introduces non-stationarity, which we address by proposing a new algorithm: Continual Deep Q-Network (DQN) Expansion (CDE). Our approach dynamically generates and adjusts Q-function subspaces to handle environmental changes and task requirements. CDE mitigates catastrophic forgetting through EWC while ensuring high plasticity using adaptive rational activation functions. Experimental results demonstrate significant improvements in learning efficiency and adaptability compared to RL baselines and other adapted methods for continual learning, highlighting the potential of our method in managing the stability-plasticity dilemma in the adaptive train scheduling setting.

Achref Jaziri, Etienne Künzel, Visvanathan Ramesh

Department of Computer Science and Mathematics, Goethe University · HessianAI, Frankfurt am Main, Germany

Stability-Plasticity Dilemma Non-Stationary RL Reinforcement Learning Deep Q-Learning Curriculum Learning Continual RL

Aug 17, 2024

Training Verifiably Robust Agents Using Set-Based Reinforcement Learning

Reinforcement learning policies parametrized by deep neural networks have achieved strong performance for continuous control, yet even small input perturbations may lead to unpredictable behavior. This sensitivity limits their use in safety-critical domains, where robustness guarantees are required. Our work addresses this gap between state-of-the-art adversarial training methods and formal verification to train verifiably robust agents. Previous works train networks with individual adversarial perturbations, making them only robust against the specific adversarial attacks used. In contrast, our approach propagates entire perturbed input sets, enclosing all possible adversarial attacks within a single network pass. We leverage this to explicitly penalize the size of the output set (minimizing closed-loop uncertainty) and thereby make the actor robust against all possible attacks. This is realized by the use of set-based policy gradients, where each output within the set has a different gradient, thereby balancing the accuracy and robustness of the network. Doing so, we achieve formal verifiability across different verification frameworks for up to 9 times larger input perturbations compared to standard reinforcement learning and improve certified worst-case performance.

Manuel Wendl, Lukas Koller, Tobias Ladner +1

Technical University of Munich, Germany

RL Control Reinforcement Learning Neural Network Robustness Certified Robustness Robust RL

Jul 31, 2024

ProSpec RL: Plan Ahead, then Execute

Imagining potential outcomes of actions before execution helps agents make more informed decisions, a prospective thinking ability fundamental to human cognition. However, mainstream model-free Reinforcement Learning (RL) methods lack the ability to proactively envision future scenarios, plan, and guide strategies. These methods typically rely on trial and error to adjust policy functions, aiming to maximize cumulative rewards or long-term value, even if such high-reward decisions place the environment in extremely dangerous states. To address this, we propose the Prospective (ProSpec) RL method, which makes higher-value, lower-risk optimal decisions by imagining future n-stream trajectories. Specifically, ProSpec employs a dynamic model to predict future states (termed "imagined states") based on the current state and a series of sampled actions. Furthermore, we integrate the concept of Model Predictive Control and introduce a cycle consistency constraint that allows the agent to evaluate and select the optimal actions from these trajectories. Moreover, ProSpec employs cycle consistency to mitigate two fundamental issues in RL: augmenting state reversibility to avoid irreversible events (low risk) and augmenting actions to generate numerous virtual trajectories, thereby improving data efficiency. We validated the effectiveness of our method on the DMControl benchmarks, where our approach achieved significant performance improvements. Code will be open-sourced upon acceptance.

Liangliang Liu, Yi Guan, BoRan Wang +5

1The Faculty of Computing, Harbin Institute of Technology, Harbin, China · 2The Artificial Intelligence Institute, Harbin Institute of Technology, ShenZhen, China · 3The Artificial Intelligence Institute, Harbin Institute of Technology, Harbin, China

Reinforcement Learning Risk-Sensitive RL Sample-Efficient RL Model-Based RL

Jul 21, 2024

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

Industry is moving toward autonomous, network-connected machines that detect and adapt to changing conditions, including hardware faults. Conventional fault-tolerant design duplicates hardware and reroutes control logic; reinforcement learning (RL) offers a learning-based alternative. This paper presents the first systematic comparison of two RL algorithms -- Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) -- for integrating fault tolerance into control. Beyond algorithm choice, we investigate four knowledge-transfer strategies: retaining or discarding model parameters, and retaining or discarding storage contents. Performance is evaluated in two Gymnasium environments: Ant-v5 and FetchReachDense-v3. Results show rapid, fault-specific recovery with clear trade-offs. In Ant-v5, retaining PPO's parameters boosts early returns and remains the safest choice across all faults, while retaining SAC's parameters yields mixed outcomes. SAC's early performance further depends on whether the replay buffer is retained: beneficial when prior experiences match current dynamics, but harmful when they diverge. In FetchReachDense-v3, discarding both PPO's and SAC's parameters was most effective under sensor corruption. Across tasks, both algorithms recover near-normal performance within minutes in low-dimensional settings and within days in high-dimensional settings, highlighting a clear trade-off between adaptation speed and asymptotic performance. These findings demonstrate that RL can deliver robust fault tolerance and offer practical guidelines.

Sheila Schoepp, Mehran Taghian, Shotaro Miwa +3

Department of Computing Science, University of Alberta, 8900 114 St NW, Edmonton, Alberta, T6G 2S4, Canada · Advanced Technology R&D Center, Mitsubishi Electric Corporation, 8-1-1,Tsukaguchi-honmachi, Amagasaki-shi, Hyogo, 661-8661, Japan · Information Technology R&D Center, Mitsubishi Electric Corporation, 5-1-1, Ofuna, Kamakura-shi, Kanagawa, 247-8501, Japan +1

RL Control Reinforcement Learning Robot Failure Recovery Fault-Tolerant Control Proximal Policy Optimization Soft Actor-Critic+2

Jul 11, 2024

Gradient Boosting Reinforcement Learning

We present Gradient Boosting Reinforcement Learning (GBRL), a framework that adapts the strengths of gradient boosting trees (GBT) to reinforcement learning (RL) tasks. While neural networks (NNs) have become the de facto choice for RL, they face significant challenges with structured and categorical features and tend to generalize poorly to out-of-distribution samples. These are challenges for which GBTs have traditionally excelled in supervised learning. However, GBT's application in RL has been limited. The design of traditional GBT libraries is optimized for static datasets with fixed labels, making them incompatible with RL's dynamic nature, where both state distributions and reward signals evolve during training. GBRL overcomes this limitation by continuously interleaving tree construction with environment interaction. Through extensive experiments, we demonstrate that GBRL outperforms NNs in domains with structured observations and categorical features while maintaining competitive performance on standard continuous control benchmarks. Like its supervised learning counterpart, GBRL demonstrates superior robustness to out-of-distribution samples and better handles irregular state-action relationships.

Benjamin Fuhrer, Chen Tessler, Gal Dalal

NVIDIA, Tel-Aviv, Israel · NVIDIA Research, Tel-Aviv, Israel.

Reinforcement Learning

May 14, 2024

Thompson Sampling for Infinite-Horizon Discounted Decision Processes

This paper develops a framework for learning in discounted infinite-horizon Markov decision processes (MDPs) with Borel state and action spaces, whose rewards and transitions depend on an unknown parameter.To analyze sampling-based adaptive learning algorithms in this setting, we introduce a canonical probability space that explicitly incorporates sampled parameters into the history of the process. As a performance criterion, we adopt the per-period suboptimality gap used in discounted-MDP regret analysis and specialize it to our parametrized Bayesian setting. Since this quantity captures the remaining loss in future performance from the current period onward, we refer to it as residual regret. We use the expected residual regret to connect discounted-MDP regret analysis with asymptotic discount optimality from adaptive control and the temporal-difference error perspective from reinforcement learning. We then focus on Thompson sampling (TS) in discounted infinite-horizon MDPs. Under assumptions that extend those used in prior work on finite state and action spaces to the Borel setting, we show that the expected residual regret for TS converges to zero exponentially fast. We further show that, under mild conditions ensuring the existence of the relevant limits, the ample-path residual regret converges to zero almost surely and TS achieves complete learning.

Daniel Adelman, Cagla Keceli, Alba V. Olivares-Nadal

Booth School of Business, The University of Chicago, Chicago, IL 60637, USA · United Airlines, Chicago, IL 60605, USA · UNSW Business School, UNSW, Kensington NSW 2033, Australia

Thompson Sampling Regret Minimization in RL Markov Decision Processes Reinforcement Learning Bayesian RL

Jan 21, 2024

TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning

Identifying the most suitable variables to represent the state is a fundamental challenge in Reinforcement Learning (RL). These variables must efficiently capture the information necessary for making optimal decisions. In order to address this problem, in this paper, we introduce the Transfer Entropy Redundancy Criterion (TERC), an information-theoretic criterion, which determines if there is entropy transferred from observable state variables to actions during training. We define an algorithm based on TERC that provably excludes variables from the observable state that do not affect the agent's policy during learning. This yields compact state representations that reduce inference time by up to 2.6 times. Our approach is policy-dependent, making it agnostic to the underlying learning algorithm. The efficiency gains we demonstrate arise at retraining and inference time on the reduced state. Our method improves both retraining and inference efficiency. We demonstrate its effectiveness across three distinct algorithm classes, namely tabular Q-learning, Actor-Critic, and Proximal Policy Optimization (PPO), evaluated in a range of environments. Furthermore, to highlight the differences between the proposed methodology and the current state-of-the-art feature selection approaches, we present a series of controlled experiments on synthetic data, before generalizing to real-world decision-making tasks. We also introduce a representation of the problem that compactly captures the transfer of information from observable state variables to actions as Bayesian networks.

Charles Westphal, Stephen Hailes, Mirco Musolesi

UCL Centre for Artificial Intelligence Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science University College London Gower Street, London WC1E 6BT, United Kingdom · Department of Computer Science and Engineering University of Bologna Viale Del Risorgimento 2, 40136 Bologna, Italy

Reinforcement Learning State Representation Learning

Nov 16, 2023

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally, RL environments run on the CPU, which limits their scalability with typical academic compute. However, recent advancements in JAX have enabled the wider use of hardware acceleration, enabling massively parallel RL training pipelines and environments. While this has been successfully applied to single-agent RL, it has not yet been widely adopted for multi-agent scenarios. In this paper, we present JaxMARL, the first open-source, Python-based library that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments and popular baseline algorithms. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is around 14 times faster than existing approaches, and up to 12500x when multiple training runs are vectorized. This enables efficient and thorough evaluations, potentially alleviating the evaluation crisis in the field. We also introduce and benchmark SMAX, a JAX-based approximate reimplementation of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. The code is available at https://github.com/flairox/jaxmarl.

Alexander Rutherford, Benjamin Ellis, Matteo Gallici +18

University of Oxford · Universitat Politècnica de Catalunya · University College London +2

RL Benchmarks Reinforcement Learning Game-Playing Agents GPU-Accelerated RL Multi-Agent Reinforcement Learning

Oct 11, 2023

Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration

Regularization is a cornerstone of modern reinforcement learning. Regularized policy iteration (RPI) provides a fundamental scheme for solving regularized Markov decision processes (RMDPs), and the widely used soft actor-critic algorithm arises as a special case when the regularizer is Shannon entropy. Despite its empirical success, the theoretical underpinnings of RPI remain unclear. In this paper, we address this gap by proving that RPI is formally equivalent to the standard Newton-Raphson method applied to the Bellman equation smoothed by strongly convex regularizers. This equivalence enables a unified convergence analysis of existing methods and supports the development of accelerated algorithms. We show that RPI enjoys local quadratic convergence; notably, for Shannon entropy, the guarantee is dimension-free. We further study RPI with inexact policy evaluation, establishing its equivalence to an inexact Newton method in which each Newton step is solved via truncated iterations, and derive an asymptotic linear convergence rate of

γ^{M}

, where

M

denotes the number of operator steps used in policy evaluation. Finally, motivated by higher-order Newton schemes, we propose a new algorithm for RMDPs that achieves third-order local convergence. Numerical experiments corroborate our theory and demonstrate the practical advantages of the proposed algorithm. Overall, our results advance the theoretical understanding of regularization in reinforcement learning and suggest new directions for efficient algorithm design.

Zeyang Li, Chuxiong Hu, Yunan Wang +4

Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, Cambridge, MA 02139, United States · Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China · College of Artificial Intelligence and the School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China

Markov Decision Processes Reinforcement Learning Policy Optimization Policy Iteration Second-Order Optimization Regularized RL

Jul 29, 2023

Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip

Reinforcement learning (RL) performs well in continuous-control tasks, but evolving hidden disturbances create partial observability: the agent must infer decision-relevant latent dynamics from interaction history. This study investigates how observation history, action history, history length, and network structure affect recurrent Twin Delayed Deep Deterministic Policy Gradient (TD3) agents. Three recurrent architectures are evaluated under controlled disturbances with different temporal characteristics. Results show that action history is particularly important when observed responses depend on previous actions, and that processing past and current action-observation information within a unified temporal sequence improves performance compared with using separate branches. We also introduce H-TD3, which reuses recurrent states generated by the actor to initialize the critic, reducing duplicated sequence processing. The architectures are further tested in a simulation-based differential-drive rover motion-regulation task under hidden asymmetric wheel slip. Recurrent architectures retain their advantage under the physically motivated multiplicative wheel-slip model, while policies trained with abstract temporally structured disturbances transfer more effectively to previously unseen wheel-slip dynamics than policies trained without disturbances. These findings provide practical guidance for recurrent RL under partial observability and evolving hidden disturbances.

Saki Omi, Hyo-Sang Shin, Namhoon Cho +2

Space Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg · School of Aerospace, Transport and Manufacturing, Cranfield University, Cranfield, U.K. · Department of Aerospace Engineering, Seoul National University, Seoul, South Korea

RL for Robotics Reinforcement Learning Partially Observable RL Robust RL

Jul 28, 2023

ETHER: Aligning Emergent Communication for Hindsight Experience Replay

Hindsight Experience Replay (HER) enhances sample efficiency in goal-conditioned reinforcement learning (RL) by relabelling failed trajectories with goals that were actually achieved. However, HER assumes access to a goal relabelling function and a predicate function that determines whether a goal has been satisfied. These assumptions break down in instruction-following tasks, where goals are expressed in natural language and differ from the state space. We formalize this as the Hindsight Reinforcement Learning problem, which shows the need to jointly learn these functions alongside the RL policy. To address it, we propose ETHER (Emergent Textual Hindsight Experience Replay), an agent that leverages Emergent Communication. ETHER uses a referential game (RG) to train a speaker and a listener to develop a grounded, artificial language describing environment states. It partially aligns this emergent language with instruction language using co-occurrence patterns between task instructions and RL observations. Experiments on BabyAI's PickupDist task show that ETHER's learned RG speaker and listener can function as the goal relabelling and predicate functions of HER, improving sample efficiency despite imperfect language alignment. Our work bridges Emergent Communication and goal-conditioned RL, opening the door to wider applications of HER.

Kevin Yandoka Denamganaï, Daniel Hernandez, Ozan Vardal +2

Department of Computer Science University of York York, UK

Reinforcement Learning Experience Replay Sample-Efficient RL Goal-Conditioned RL Hindsight Experience Replay Emergent Communication

Jun 23, 2023

Reinforcement Learning with Temporal-Logic-Based Causal Diagrams

We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and integrate them into the state-space for RL algorithms. However, while these machines model the reward function, they often overlook the causal knowledge about the environment. To address this limitation, we propose the Temporal-Logic-based Causal Diagram (TL-CD) in RL, which captures the temporal causal relationships between different properties of the environment. We exploit the TL-CD to devise an RL algorithm in which an agent requires significantly less exploration of the environment. To this end, based on a TL-CD and a task DFA, we identify configurations where the agent can determine the expected rewards early during an exploration. Through a series of case studies, we demonstrate the benefits of using TL-CDs, particularly the faster convergence of the algorithm to an optimal policy due to reduced exploration of the environment.

Yash Paliwal, Rajarshi Roy, Jean-Raphaël Gaglione +5

Arizona State University, Arizona, USA · Max Planck Institute for Software Systems, Kaiserslautern, Germany · University of Texas at Austin, Texas, USA +3

Reinforcement Learning Causal RL Sample-Efficient RL

Apr 20, 2023

Topology-Guided Modular Actor-Critic Learning for Continuous Systems under Temporal Objectives

We study formal policy synthesis for continuous-state stochastic systems under linear temporal logic specifications. The product of the system with the automaton of the specification has a hybrid state space with sparse rewards. We introduce a generalized optimal backup order, defined in reverse to a topological order over automaton states, that guides value backups and provably preserves optimality. We further present a model-free actor-critic algorithm whose policy evaluation solves a constrained optimization problem by the augmented Lagrangian method, yielding hyperparameter self-tuning, and prove its optimality and convergence in the tabular case. Since integer encodings of automaton states impose a spurious ordinal relationship on functions learned by one network, we dedicate a value and a policy network to each automaton state (modular learning). The algorithm matches or outperforms PPO, DQN, and A2C on CartPole, and on a Dubins car under a temporal specification the topological order and modular learning raise the success rate from 26.0% to 71.5%.

Lening Li, Zhentian Qian, Jianan Xia +7

Ningbo University, Ningbo, China · Robotics Engineering Program, Worcester Polytechnic Institute, Worcester, MA, USA · Ningbo Zhenhai Silver-Ball Bearing Co., Ltd., Ningbo, China

RL Control Reinforcement Learning Model-Free RL Actor-Critic Methods Policy Learning

Oct 7, 2022

Stackelberg POMDP: Learning to Lead via Reinforcement Learning

Many real-world domains--including e-commerce platform design, security planning, and multi-agent coordination--feature leader-follower problems where one decision-maker commits to a policy and others react strategically. We develop a reinforcement learning framework for such interactions in sequential environments with partial observations and multiple followers. Followers may adapt through no-regret learning or reinforcement learning, potentially departing from equilibrium behavior. The framework embeds follower adaptation into the leader's environment to construct a single-agent partially observable Markov decision process--the Stackelberg POMDP. For policy-interactive response algorithms, which access the leader's policy through queries, we prove that an optimal policy based only on the leader's game history yields an optimal commitment under the specified response procedure. We use proximal policy optimization with a centralized critic and train contextual meta-followers to respond across leader policies. In indirect mechanism design, mechanisms using buyer messages achieve higher social welfare than optimal standard sequential price mechanisms across all tested type counts, with responses certified as approximate Bayesian coarse correlated equilibria. In platform design, learned display rules increase mean consumer surplus by 8.4% over an optimized fixed price cap while accommodating hidden seller costs. In Atari bilateral trade, meta-learned follower responses support joint learning of visual gameplay and economic decisions; assigning leadership to the seller or buyer shifts transaction prices and payoffs in that agent's favor. Controlled ablations examine how response credit, policy consistency, and reward timing affect learning.

Matthias Gerstgrasser, Gianluca Brero, Alon Eden +6

John A. Paulson School of Engineering and Applied Sciences, Harvard University · Data Science Initiative, Brown University · School of Computer Science and Engineering, Hebrew University of Jerusalem +2

Game-Theoretic RL Reinforcement Learning Multi-Agent Reinforcement Learning Partially Observable Markov Decision Processes Mechanism Design