{"total":100,"rows":[{"id":"2103.10897","title":"Bilinear Classes: A Structural Framework for Provable Generalization in RL","created":"2021-03-19","cited_by_count":178,"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":"2102.07035","title":"Model-free Representation Learning and Exploration in Low-rank MDPs","created":"2021-02-14","cited_by_count":82,"area":null},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68,"area":"wm"},{"id":"2203.05804","title":"Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism","created":"2022-03-11","cited_by_count":65,"area":"offlinerl"},{"id":"2212.06132","title":"Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processes","created":"2022-12-12","cited_by_count":57,"area":null},{"id":"2205.11507","title":"Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs","created":"2022-05-23","cited_by_count":52,"area":null},{"id":"2201.11206","title":"Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes","created":"2022-01-26","cited_by_count":49,"area":null},{"id":"2101.12745","title":"Improved Variance-Aware Confidence Sets for Linear Bandits and Linear Mixture MDP","created":"2021-01-29","cited_by_count":45,"area":null},{"id":"2103.12690","title":"An Exponential Lower Bound for Linearly-Realizable MDPs with Constant Suboptimality Gap","created":"2021-03-23","cited_by_count":40,"area":null},{"id":"2302.10371","title":"Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency","created":"2023-02-21","cited_by_count":40,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2203.13935","title":"Offline Reinforcement Learning Under Value and Density-Ratio Realizability: The Power of Gaps","created":"2022-03-25","cited_by_count":34,"area":"offlinerl"},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2206.07659","title":"Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity","created":"2022-06-15","cited_by_count":32,"area":null},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"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":"2206.11489","title":"Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation","created":"2022-06-23","cited_by_count":30,"area":null},{"id":"2301.08215","title":"Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient","created":"2023-01-19","cited_by_count":30,"area":null},{"id":"2110.06394","title":"Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation","created":"2021-10-12","cited_by_count":29,"area":null},{"id":"2305.08841","title":"A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes","created":"2023-05-15","cited_by_count":29,"area":null},{"id":"2102.08940","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","created":"2021-02-17","cited_by_count":28,"area":null},{"id":"2110.08847","title":"Provable RL with Exogenous Distractors via Multistep Inverse Dynamics","created":"2021-10-17","cited_by_count":28,"area":null},{"id":"2206.10770","title":"On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL","created":"2022-06-21","cited_by_count":27,"area":null},{"id":"2102.07404","title":"Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games","created":"2021-02-15","cited_by_count":25,"area":null},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"id":"2110.12727","title":"Learning Stochastic Shortest Path with Linear Function Approximation","created":"2021-10-25","cited_by_count":23,"area":null},{"id":"2305.18258","title":"Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2102.02049","title":"On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function","created":"2021-02-03","cited_by_count":18,"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":"2105.14016","title":"Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model","created":"2021-05-28","cited_by_count":18,"area":null},{"id":"2502.01930","title":"Robust LLM Alignment via Distributionally Robust Direct Preference Optimization","created":"2025-02-04","cited_by_count":18,"area":"alignment"},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2301.13087","title":"Improved Regret for Efficient Online Reinforcement Learning with Linear Function Approximation","created":"2023-01-30","cited_by_count":17,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2110.08984","title":"Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPs","created":"2021-10-18","cited_by_count":16,"area":null},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2106.11612","title":"Uniform-PAC Bounds for Reinforcement Learning with Linear Function Approximation","created":"2021-06-22","cited_by_count":14,"area":null},{"id":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2305.11283","title":"On the Statistical Efficiency of Mean-Field Reinforcement Learning with General Function Approximation","created":"2023-05-18","cited_by_count":14,"area":null},{"id":"2306.06836","title":"Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds","created":"2023-06-12","cited_by_count":14,"area":null},{"id":"2307.02842","title":"Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback","created":"2023-07-06","cited_by_count":14,"area":"alignment"},{"id":"2308.14642","title":"Rate-Optimal Policy Optimization for Linear Markov Decision Processes","created":"2023-08-28","cited_by_count":14,"area":null},{"id":"2311.15238","title":"A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation","created":"2023-11-26","cited_by_count":14,"area":null},{"id":"2402.12570","title":"Offline Multi-task Transfer RL with Representational Penalization","created":"2024-02-19","cited_by_count":14,"area":"offlinerl"},{"id":"2106.11519","title":"Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations","created":"2021-06-22","cited_by_count":13,"area":null},{"id":"2110.10133","title":"Locally Differentially Private Reinforcement Learning for Linear Mixture Markov Decision Processes","created":"2021-10-19","cited_by_count":13,"area":null},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2212.13540","title":"Model-Based Reinforcement Learning with Multinomial Logistic Function Approximation","created":"2022-12-27","cited_by_count":13,"area":null},{"id":"2106.11935","title":"Provably Efficient Representation Selection in Low-rank Markov Decision Processes: From Online to Offline RL","created":"2021-06-22","cited_by_count":12,"area":"offlinerl"},{"id":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"id":"2303.00694","title":"The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms","created":"2023-03-01","cited_by_count":12,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2211.14250","title":"Model-Free Reinforcement Learning with the Decision-Estimation Coefficient","created":"2022-11-25","cited_by_count":11,"area":null},{"id":"2201.11965","title":"Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints","created":"2022-01-28","cited_by_count":10,"area":null},{"id":"2302.10796","title":"Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret","created":"2023-02-21","cited_by_count":9,"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":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","cited_by_count":8,"area":null},{"id":"2303.10165","title":"Optimal Horizon-Free Reward-Free Exploration for Linear Mixture MDPs","created":"2023-03-17","cited_by_count":7,"area":null},{"id":"2306.10694","title":"On the Model-Misspecification in Reinforcement Learning","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2509.08660","title":"Replicable Reinforcement Learning with Linear Function Approximation","created":"2025-09-10","cited_by_count":7,"area":"deeprl"},{"id":"2109.05546","title":"Improved Algorithms for Misspecified Linear Markov Decision Processes","created":"2021-09-12","cited_by_count":6,"area":null},{"id":"2403.10738","title":"Horizon-Free Regret for Linear Markov Decision Processes","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2112.14195","title":"Exponential Family Model-Based Reinforcement Learning via Score Matching","created":"2021-12-28","cited_by_count":5,"area":null},{"id":"2206.00796","title":"Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2407.03065","title":"Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes","created":"2024-07-03","cited_by_count":5,"area":"deeprl"},{"id":"2201.08732","title":"Meta Learning MDPs with Linear Transition Models","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2204.10349","title":"Provably Efficient Kernelized Q-Learning","created":"2022-04-21","cited_by_count":4,"area":null},{"id":"2302.12940","title":"Exponential Hardness of Reinforcement Learning with Linear Function Approximation","created":"2023-02-25","cited_by_count":4,"area":null},{"id":"2312.04464","title":"Horizon-Free and Instance-Dependent Regret Bounds for Reinforcement Learning with General Function Approximation","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2410.24089","title":"Demystifying Linear MDPs and Novel Dynamics Aggregation Framework","created":"2024-10-31","cited_by_count":4,"area":null},{"id":"2202.05444","title":"Computational-Statistical Gaps in Reinforcement Learning","created":"2022-02-11","cited_by_count":3,"area":null},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2305.08350","title":"Uniform-PAC Guarantees for Model-Based RL with Bounded Eluder Dimension","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2404.10745","title":"Achieving Constant Regret in Linear Markov Decision Processes","created":"2024-04-16","cited_by_count":3,"area":"deeprl"},{"id":"2502.09780","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","created":"2025-02-13","cited_by_count":3,"area":null},{"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":"2310.11515","title":"Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2403.11175","title":"Prior-dependent analysis of posterior sampling reinforcement learning with function approximation","created":"2024-03-17","cited_by_count":2,"area":"deeprl"},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2208.05363","title":"Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium","created":"2022-08-10","cited_by_count":1,"area":null},{"id":"2306.12981","title":"Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping","created":"2023-06-22","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","cited_by_count":1,"area":null},{"id":"2402.08998","title":"Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path","created":"2024-02-14","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":"2605.00654","title":"Reinforcement Learning with Markov Risk Measures and Multipattern Risk Approximation","created":"2026-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2605.10909","title":"Revisiting Policy Gradients for Restricted Policy Classes: Escaping Myopic Local Optima with $k$-step Policy Gradients","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2606.25170","title":"Minimax PAC Bounds for Learning in Exogenous Contextual MDPs","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.31524","title":"On the Convergence of Self-Improving Online LLM Alignment","created":"2026-06-30","cited_by_count":1,"area":"alignment"},{"id":"2609.00193","title":"Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost","created":"2026-08-31","cited_by_count":1,"area":"deeprl"},{"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":"2607.01715","title":"Distributionally Robust Listwise Preference Optimization","created":"2026-07-02","cited_by_count":0,"area":"alignment"},{"id":"2609.07998","title":"Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study","created":"2026-09-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}