{"total":71,"rows":[{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228,"area":"agents"},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2202.04634","title":"Offline Reinforcement Learning with Realizability and Single-policy Concentrability","created":"2022-02-09","cited_by_count":123,"area":"offlinerl"},{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"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":"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":"2211.00716","title":"Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian","created":"2022-11-01","cited_by_count":29,"area":"offlinerl"},{"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":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2303.17396","title":"Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions","created":"2023-03-30","cited_by_count":26,"area":"offlinerl"},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2205.10671","title":"Pessimism for Offline Linear Contextual Bandits using $\\ell_p$ Confidence Sets","created":"2022-05-21","cited_by_count":18,"area":null},{"id":"2207.05837","title":"Learning Bellman Complete Representations for Offline Policy Evaluation","created":"2022-07-12","cited_by_count":17,"area":"offlinerl"},{"id":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"area":null},{"id":"2211.00164","title":"Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information","created":"2022-10-31","cited_by_count":16,"area":"offlinerl"},{"id":"2212.13861","title":"Offline Reinforcement Learning via Linear-Programming with Error-Bound Induced Constraints","created":"2022-12-28","cited_by_count":15,"area":"offlinerl"},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2310.11428","title":"Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"id":"2302.05404","title":"Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness","created":"2023-02-10","cited_by_count":13,"area":null},{"id":"2307.12975","title":"Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems","created":"2023-07-24","cited_by_count":13,"area":"alignment"},{"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":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"area":"offlinerl"},{"id":"2307.04354","title":"Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data","created":"2023-07-10","cited_by_count":11,"area":null},{"id":"2311.08384","title":"Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees","created":"2023-11-14","cited_by_count":11,"area":"offlinerl"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2306.07818","title":"A Primal-Dual-Critic Algorithm for Offline Constrained Reinforcement Learning","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2310.06113","title":"When is Agnostic Reinforcement Learning Statistically Tractable?","created":"2023-10-09","cited_by_count":9,"area":null},{"id":"2306.13601","title":"Active Coverage for PAC Reinforcement Learning","created":"2023-06-23","cited_by_count":8,"area":null},{"id":"2403.05385","title":"Switching the Loss Reduces the Cost in Batch (Offline) Reinforcement Learning","created":"2024-03-08","cited_by_count":8,"area":"offlinerl"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2203.04236","title":"A Complete Characterization of Linear Estimators for Offline Policy Evaluation","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2210.05158","title":"Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning","created":"2022-10-11","cited_by_count":6,"area":"offlinerl"},{"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":"2406.15753","title":"The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret","created":"2024-06-22","cited_by_count":6,"area":"alignment"},{"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":"2509.21172","title":"Inverse Reinforcement Learning with Just Classification and a Few Regressions","created":"2025-09-25","cited_by_count":5,"area":"offlinerl"},{"id":"2306.07528","title":"Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective","created":"2023-06-13","cited_by_count":4,"area":"offlinerl"},{"id":"2401.12216","title":"Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning","created":"2024-01-22","cited_by_count":4,"area":"deeprl"},{"id":"2403.07916","title":"Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization","created":"2024-02-27","cited_by_count":4,"area":"deeprl"},{"id":"2405.05468","title":"Model-Free Robust $\\phi$-Divergence Reinforcement Learning Using Both Offline and Online Data","created":"2024-05-08","cited_by_count":4,"area":"deeprl"},{"id":"2406.11686","title":"The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation","created":"2024-06-17","cited_by_count":4,"area":"offlinerl"},{"id":"2410.17538","title":"Primal-Dual Spectral Representation for Off-policy Evaluation","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2302.12780","title":"VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation","created":"2023-02-24","cited_by_count":3,"area":"offlinerl"},{"id":"2307.13332","title":"The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation","created":"2023-07-25","cited_by_count":3,"area":null},{"id":"2405.16809","title":"Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\\pi$-Realizability and Concentrability","created":"2024-05-27","cited_by_count":3,"area":"offlinerl"},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2212.08232","title":"Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling","created":"2022-12-16","cited_by_count":2,"area":"offlinerl"},{"id":"2501.06339","title":"On The Statistical Complexity of Offline Decision-Making","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2510.17391","title":"Finite-Time Bounds for Average-Reward Fitted Q-Iteration","created":"2025-10-20","cited_by_count":2,"area":"offlinerl"},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2608.25756","title":"TailSFT: Filtered Fine-Tuning Improves Post-Training Performance","created":"2026-08-26","cited_by_count":2,"area":"agents"},{"id":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2601.20765","title":"Less is More: Clustered Cross-Covariance Control for Offline RL","created":"2026-01-28","cited_by_count":1,"area":"offlinerl"},{"id":"2607.05375","title":"Fitted Occupancy-Ratio Evaluation without Bellman Completeness","created":"2026-07-06","cited_by_count":1,"area":"offlinerl"},{"id":"2302.00284","title":"Selective Uncertainty Propagation in Offline RL","created":"2023-02-01","cited_by_count":0,"area":"offlinerl"},{"id":"2406.01378","title":"A Fast Convergence Theory for Offline Decision Making","created":"2024-06-03","cited_by_count":0,"area":"offlinerl"},{"id":"2506.09940","title":"The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2510.03494","title":"Trajectory Data Suffices for Statistically Efficient Policy Evaluation in Fixed-Horizon Offline RL with Linear $q^\\pi$-Realizability and Concentrability","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2602.06930","title":"Continuous-time reinforcement learning: ellipticity enables model-free value function approximation","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.12107","title":"On the Complexity of Offline Reinforcement Learning with $Q^\\star$-Approximation and Partial Coverage","created":"2026-02-12","cited_by_count":0,"area":"offlinerl"},{"id":"2605.05791","title":"Fitted Q-Iteration with Continuous Actions and Adaptive Data: Smoothed Coverage and Minimax Rates","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.05833","title":"On the Role of Language Representations in Auto-Bidding: Findings and Implications","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.06474","title":"Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.30843","title":"A Lecture Note on Offline RL and IRL, Part II: Foundations of Inverse Reinforcement Learning and Dynamic Discrete Choice Models","created":"2026-05-29","cited_by_count":0,"area":"offlinerl"},{"id":"2606.18531","title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","created":"2026-06-16","cited_by_count":0,"area":"lr"},{"id":"2608.07772","title":"The Sample Complexity of Policy Learning with Mu-Resets","created":"2026-08-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}