{"total":52,"rows":[{"id":"2102.00815","title":"Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms","created":"2021-02-01","cited_by_count":223,"area":null},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2110.04652","title":"Representation Learning for Online and Offline RL in Low-rank MDPs","created":"2021-10-09","cited_by_count":129,"area":"offlinerl"},{"id":"2101.02195","title":"Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints","created":"2021-01-06","cited_by_count":124,"area":null},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51,"area":"offlinerl"},{"id":"2106.03352","title":"The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces","created":"2021-06-07","cited_by_count":48,"area":null},{"id":"2307.13586","title":"Settling the Sample Complexity of Online Reinforcement Learning","created":"2023-07-25","cited_by_count":45,"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":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34,"area":null},{"id":"2209.15634","title":"A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning","created":"2022-09-30","cited_by_count":31,"area":null},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27,"area":"offlinerl"},{"id":"2203.12922","title":"Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies","created":"2022-03-24","cited_by_count":27,"area":null},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2306.07745","title":"Kernelized Reinforcement Learning with Order Optimal Regret Bounds","created":"2023-06-13","cited_by_count":20,"area":null},{"id":"2206.14332","title":"Active Exploration via Experiment Design in Markov Chains","created":"2022-06-29","cited_by_count":19,"area":null},{"id":"2301.13446","title":"Sharp Variance-Dependent Bounds in Reinforcement Learning: Best of Both Worlds in Stochastic and Deterministic Environments","created":"2023-01-31","cited_by_count":19,"area":null},{"id":"2111.00633","title":"Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning","created":"2021-11-01","cited_by_count":18,"area":null},{"id":"2202.10678","title":"Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning","created":"2022-02-22","cited_by_count":18,"area":null},{"id":"2207.05852","title":"Optimistic PAC Reinforcement Learning: the Instance-Dependent View","created":"2022-07-12","cited_by_count":17,"area":null},{"id":"2102.09703","title":"Near-Optimal Randomized Exploration for Tabular Markov Decision Processes","created":"2021-02-19","cited_by_count":15,"area":null},{"id":"2402.07868","title":"Nesting Particle Filters for Experimental Design in Dynamical Systems","created":"2024-02-12","cited_by_count":12,"area":null},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2305.06446","title":"Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation","created":"2023-05-10","cited_by_count":9,"area":null},{"id":"2210.12057","title":"Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","cited_by_count":8,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2502.10138","title":"Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation","created":"2025-02-14","cited_by_count":6,"area":"deeprl"},{"id":"2111.07615","title":"Optimism and Delays in Episodic Reinforcement Learning","created":"2021-11-15","cited_by_count":5,"area":null},{"id":"2210.11604","title":"Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2305.08359","title":"Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs","created":"2023-05-15","cited_by_count":4,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2205.09056","title":"Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs","created":"2022-05-18","cited_by_count":2,"area":null},{"id":"2405.13755","title":"Offline RL via Feature-Occupancy Gradient Ascent","created":"2024-05-22","cited_by_count":2,"area":"offlinerl"},{"id":"2406.09563","title":"e-COP : Episodic Constrained Optimization of Policies","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2504.05585","title":"TW-CRL: Time-Weighted Contrastive Reward Learning for Efficient Inverse Reinforcement Learning","created":"2025-04-08","cited_by_count":2,"area":"offlinerl"},{"id":"2402.09113","title":"How does Your RL Agent Explore? An Optimal Transport Analysis of Occupancy Measure Trajectories","created":"2024-02-14","cited_by_count":1,"area":null},{"id":"2502.07715","title":"Near-Optimal Sample Complexity in Reward-Free Kernel-Based Reinforcement Learning","created":"2025-02-11","cited_by_count":1,"area":"deeprl"},{"id":"2206.05200","title":"Dynamic mean field programming","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2208.00330","title":"Convex duality for stochastic shortest path problems in known and unknown environments","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2407.13622","title":"Misspecified $Q$-Learning with Sparse Linear Function Approximation: Tight Bounds on Approximation Error","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2511.03473","title":"Reinforcement Learning Using known Invariances","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2605.15692","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2607.06935","title":"Mathematical methods of reinforcement learning","created":"2026-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2607.19854","title":"Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependence","created":"2026-07-22","cited_by_count":0,"area":"deeprl"},{"id":"2609.36486","title":"Optimal Multi-Reward Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}