{"total":82,"rows":[{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2110.03239","title":"Understanding Domain Randomization for Sim-to-real Transfer","created":"2021-10-07","cited_by_count":80,"area":null},{"id":"2107.08346","title":"Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses","created":"2021-07-18","cited_by_count":52,"area":null},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46,"area":"wm"},{"id":"2102.05261","title":"Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States","created":"2021-02-10","cited_by_count":43,"area":null},{"id":"2104.11186","title":"Stochastic Shortest Path: Minimax, Parameter-Free and Towards Horizon-Free Regret","created":"2021-04-22","cited_by_count":34,"area":null},{"id":"2106.07329","title":"On-Policy Deep Reinforcement Learning for the Average-Reward Criterion","created":"2021-06-14","cited_by_count":30,"area":null},{"id":"2202.00150","title":"Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints","created":"2022-01-31","cited_by_count":29,"area":null},{"id":"2306.16394","title":"Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes","created":"2023-06-28","cited_by_count":29,"area":null},{"id":"2309.01922","title":"Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes","created":"2023-09-05","cited_by_count":26,"area":null},{"id":"2210.08863","title":"You Only Live Once: Single-Life Reinforcement Learning","created":"2022-10-17","cited_by_count":24,"area":null},{"id":"2106.08377","title":"Implicit Finite-Horizon Approximation and Efficient Optimal Algorithms for Stochastic Shortest Path","created":"2021-06-15","cited_by_count":23,"area":null},{"id":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"id":"2301.00858","title":"Robust Average-Reward Markov Decision Processes","created":"2023-01-02","cited_by_count":22,"area":null},{"id":"2102.07301","title":"Nearly Minimax Optimal Regret for Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation","created":"2021-02-15","cited_by_count":18,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2203.03535","title":"Influencing Long-Term Behavior in Multiagent Reinforcement Learning","created":"2022-03-07","cited_by_count":18,"area":null},{"id":"2102.12661","title":"Online Learning for Unknown Partially Observable MDPs","created":"2021-02-25","cited_by_count":17,"area":null},{"id":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2302.09408","title":"Best of Both Worlds Policy Optimization","created":"2023-02-18","cited_by_count":17,"area":null},{"id":"2403.11477","title":"Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs","created":"2024-03-18","cited_by_count":17,"area":null},{"id":"2106.05335","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2406.01234","title":"Achieving Tractable Minimax Optimal Regret in Average Reward MDPs","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2407.18878","title":"A Sharper Global Convergence Analysis for Average Reward Reinforcement Learning via an Actor-Critic Approach","created":"2024-07-26","cited_by_count":15,"area":"deeprl"},{"id":"2310.02147","title":"Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2404.02108","title":"Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs","created":"2024-04-02","cited_by_count":14,"area":"deeprl"},{"id":"2402.02042","title":"Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm","created":"2024-02-03","cited_by_count":9,"area":"deeprl"},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9,"area":"deeprl"},{"id":"2202.13187","title":"Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2505.15138","title":"Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm","created":"2025-05-21","cited_by_count":8,"area":"deeprl"},{"id":"2405.15050","title":"Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs","created":"2024-05-23","cited_by_count":7,"area":"deeprl"},{"id":"2502.16816","title":"Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning","created":"2025-02-24","cited_by_count":7,"area":"deeprl"},{"id":"2505.19986","title":"Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach","created":"2025-05-26","cited_by_count":7,"area":"deeprl"},{"id":"2301.11547","title":"Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation","created":"2023-01-27","cited_by_count":6,"area":null},{"id":"2302.07477","title":"Optimal Sample Complexity of Stable Discounted Markov Decision Processes","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2404.12648","title":"Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation","created":"2024-04-19","cited_by_count":6,"area":null},{"id":"2410.23498","title":"Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm","created":"2024-10-30","cited_by_count":6,"area":"deeprl"},{"id":"2306.08803","title":"Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning","created":"2023-06-15","cited_by_count":5,"area":null},{"id":"2311.13469","title":"Span-Based Optimal Sample Complexity for Average Reward MDPs","created":"2023-11-22","cited_by_count":5,"area":null},{"id":"2403.05738","title":"Provable Policy Gradient Methods for Average-Reward Markov Potential Games","created":"2024-03-09","cited_by_count":5,"area":"deeprl"},{"id":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5,"area":"offlinerl"},{"id":"2410.15557","title":"How to Find the Exact Pareto Front for Multi-Objective MDPs?","created":"2024-10-21","cited_by_count":5,"area":null},{"id":"2502.11238","title":"Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2109.03396","title":"A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent","created":"2021-09-08","cited_by_count":4,"area":null},{"id":"2211.15931","title":"Posterior Sampling for Continuing Environments","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2307.04957","title":"Reinforcement Learning with Non-Cumulative Objective","created":"2023-07-11","cited_by_count":4,"area":null},{"id":"2506.07040","title":"Efficient Q-Learning and Actor-Critic Methods for Robust Average-Reward Reinforcement Learning","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2210.13075","title":"Hardness in Markov Decision Processes: Theory and Practice","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2301.02389","title":"Provable Reset-free Reinforcement Learning by No-Regret Reduction","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2303.12981","title":"Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2310.11684","title":"Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2601.13642","title":"Sample Complexity of Average-Reward Q-Learning: From Single-agent to Federated Reinforcement Learning","created":"2026-01-20","cited_by_count":3,"area":"deeprl"},{"id":"2602.18003","title":"Policy Gradient Algorithms in Average-Reward Multichain MDPs","created":"2026-02-20","cited_by_count":3,"area":"deeprl"},{"id":"2606.16729","title":"Learning Policy from a Single Trajectory in Average-Reward Markov Decision Process","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2407.10207","title":"Learning to Steer Markovian Agents under Model Uncertainty","created":"2024-07-14","cited_by_count":2,"area":null},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2504.09035","title":"InterQ: A DQN Framework for Optimal Intermittent Control","created":"2025-04-12","cited_by_count":2,"area":"deeprl"},{"id":"2506.24005","title":"Provably Efficient and Agile Randomized Q-Learning","created":"2025-06-30","cited_by_count":2,"area":"deeprl"},{"id":"2510.17391","title":"Finite-Time Bounds for Average-Reward Fitted Q-Iteration","created":"2025-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2603.00945","title":"Non-Rectangular Average-Reward Robust MDPs: Optimal Policies and Their Transient Values","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2605.11586","title":"Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret","created":"2026-05-12","cited_by_count":2,"area":"deeprl"},{"id":"2106.15503","title":"Curious Explorer: a provable exploration strategy in Policy Learning","created":"2021-06-29","cited_by_count":1,"area":null},{"id":"2112.10314","title":"Balancing Adaptability and Non-exploitability in Repeated Games","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2211.15792","title":"Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2410.14992","title":"Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2411.06069","title":"Model Selection for Average Reward RL with Application to Utility Maximization in Repeated Games","created":"2024-11-09","cited_by_count":1,"area":null},{"id":"2507.22854","title":"A Bit of Freedom Goes a Long Way: Classical and Quantum Algorithms for Reinforcement Learning under a Generative Model","created":"2025-07-30","cited_by_count":1,"area":"deeprl"},{"id":"2603.10895","title":"Ergodicity in reinforcement learning","created":"2026-03-11","cited_by_count":1,"area":"deeprl"},{"id":"2202.10008","title":"Double Thompson Sampling in Finite stochastic Games","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2301.05630","title":"Decentralized model-free reinforcement learning in stochastic games with average-reward objective","created":"2023-01-13","cited_by_count":0,"area":null},{"id":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2306.06402","title":"A Single-Loop Deep Actor-Critic Algorithm for Constrained Reinforcement Learning with Provable Convergence","created":"2023-06-10","cited_by_count":0,"area":null},{"id":"2308.02391","title":"Learning Optimal Admission Control in Partially Observable Queueing Networks","created":"2023-08-04","cited_by_count":0,"area":null},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2504.08200","title":"Influential Bandits: Pulling an Arm May Change the Environment","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.15693","title":"Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2602.00781","title":"Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding","created":"2026-01-31","cited_by_count":0,"area":"deeprl"},{"id":"2603.04353","title":"A Constrained RL Approach for Cost-Efficient Delivery of Latency-Sensitive Applications","created":"2026-03-04","cited_by_count":0,"area":"deeprl"},{"id":"2606.25012","title":"Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL","created":"2026-06-23","cited_by_count":0,"area":"deeprl"},{"id":"2608.07725","title":"Finite Constant Frontiers and Auditable Regret Certificates for Average-Reward Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2609.39093","title":"Learning Infinite-Horizon Average-Reward CMDPs via State Augmentation","created":"2026-09-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}