{"total":99,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279,"area":"offlinerl"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2107.06226","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage","created":"2021-07-13","cited_by_count":164,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2302.01877","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","created":"2023-02-03","cited_by_count":149,"area":"diffusion"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2202.13890","title":"Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity","created":"2022-02-28","cited_by_count":85,"area":"offlinerl"},{"id":"2110.08695","title":"Towards Instance-Optimal Offline Reinforcement Learning with Pessimism","created":"2021-10-17","cited_by_count":78,"area":"offlinerl"},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2102.05371","title":"Risk-Averse Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":65,"area":"offlinerl"},{"id":"2206.13464","title":"When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning","created":"2022-06-27","cited_by_count":60,"area":"offlinerl"},{"id":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51,"area":"offlinerl"},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2309.12696","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning","created":"2023-09-22","cited_by_count":37,"area":"offlinerl"},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2105.07351","title":"Model-Based Offline Planning with Trajectory Pruning","created":"2021-05-16","cited_by_count":30,"area":"offlinerl"},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"id":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"id":"2106.03207","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage","created":"2021-06-06","cited_by_count":26,"area":"offlinerl"},{"id":"2205.13589","title":"Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes","created":"2022-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2111.13807","title":"Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization","created":"2021-11-27","cited_by_count":25,"area":"offlinerl"},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2310.04413","title":"Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-10-06","cited_by_count":24,"area":"offlinerl"},{"id":"2210.09241","title":"Boosting Offline Reinforcement Learning via Data Rebalancing","created":"2022-10-17","cited_by_count":22,"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":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21,"area":"offlinerl"},{"id":"2302.10342","title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","created":"2023-02-20","cited_by_count":19,"area":null},{"id":"2010.08891","title":"DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs","created":"2020-10-18","cited_by_count":16,"area":"offlinerl"},{"id":"2205.15827","title":"Robust Anytime Learning of Markov Decision Processes","created":"2022-05-31","cited_by_count":16,"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":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","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":"2206.06426","title":"Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward","created":"2022-06-13","cited_by_count":13,"area":"offlinerl"},{"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":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"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":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2310.18434","title":"Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage","created":"2023-10-27","cited_by_count":12,"area":"offlinerl"},{"id":"2408.10556","title":"Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks","created":"2024-08-20","cited_by_count":11,"area":"offlinerl"},{"id":"2102.11327","title":"Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning","created":"2021-02-22","cited_by_count":10,"area":"offlinerl"},{"id":"2201.12594","title":"Robust Imitation Learning from Corrupted Demonstrations","created":"2022-01-29","cited_by_count":10,"area":"offlinerl"},{"id":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","cited_by_count":9,"area":"offlinerl"},{"id":"2402.15392","title":"Offline Inverse RL: New Solution Concepts and Provably Efficient Algorithms","created":"2024-02-23","cited_by_count":9,"area":"offlinerl"},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2103.06671","title":"Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks","created":"2021-03-11","cited_by_count":8,"area":"offlinerl"},{"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":"2503.06810","title":"Mitigating Preference Hacking in Policy Optimization with Pessimism","created":"2025-03-10","cited_by_count":8,"area":"alignment"},{"id":"2207.00632","title":"Offline Policy Optimization with Eligible Actions","created":"2022-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2210.14420","title":"Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2301.05664","title":"Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning","created":"2023-01-13","cited_by_count":6,"area":"offlinerl"},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"id":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2110.02304","title":"You Only Evaluate Once: a Simple Baseline Algorithm for Offline RL","created":"2021-10-05","cited_by_count":4,"area":"offlinerl"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"id":"2207.08956","title":"Online Learning with Off-Policy Feedback","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2212.02125","title":"TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets","created":"2022-12-05","cited_by_count":4,"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":"2307.08840","title":"Bayesian Safe Policy Learning with Chance Constrained Optimization: Application to Military Security Assessment during the Vietnam War","created":"2023-07-17","cited_by_count":4,"area":null},{"id":"2401.03786","title":"Long-term Safe Reinforcement Learning with Binary Feedback","created":"2024-01-08","cited_by_count":4,"area":"deeprl"},{"id":"2205.12418","title":"Tiered Reinforcement Learning: Pessimism in the Face of Uncertainty and Constant Regret","created":"2022-05-25","cited_by_count":3,"area":null},{"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":"2305.13289","title":"Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach","created":"2023-05-22","cited_by_count":3,"area":"offlinerl"},{"id":"2307.13824","title":"Offline Reinforcement Learning with On-Policy Q-Function Regularization","created":"2023-07-25","cited_by_count":3,"area":"offlinerl"},{"id":"2405.15332","title":"Cross-Validated Off-Policy Evaluation","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2509.19305","title":"Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning","created":"2025-09-04","cited_by_count":3,"area":"diffusion"},{"id":"2602.19917","title":"Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learning","created":"2026-02-23","cited_by_count":3,"area":"offlinerl"},{"id":"2605.01248","title":"$S^3$-R1: Learning to Retrieve and Answer Step-by-Step with Synthetic Data","created":"2026-05-02","cited_by_count":3,"area":"lr"},{"id":"2106.09973","title":"The Curse of Passive Data Collection in Batch Reinforcement Learning","created":"2021-06-18","cited_by_count":2,"area":null},{"id":"2209.07148","title":"Semi-supervised Batch Learning From Logged Data","created":"2022-09-15","cited_by_count":2,"area":null},{"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":"2301.10330","title":"Off-Policy Evaluation for Action-Dependent Non-Stationary Environments","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2303.11187","title":"A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations","created":"2023-03-20","cited_by_count":2,"area":null},{"id":"2312.17168","title":"Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?","created":"2023-12-28","cited_by_count":2,"area":"offlinerl"},{"id":"2110.03165","title":"Offline RL With Resource Constrained Online Deployment","created":"2021-10-07","cited_by_count":1,"area":"offlinerl"},{"id":"2505.17717","title":"A Distributionally Robust Framework for Nuisance in Causal Effect Estimation","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.14058","title":"Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning","created":"2025-06-16","cited_by_count":1,"area":"offlinerl"},{"id":"2203.01758","title":"On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency","created":"2022-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2206.05521","title":"Model-based Offline Imitation Learning with Non-expert Data","created":"2022-06-11","cited_by_count":0,"area":"offlinerl"},{"id":"2211.14827","title":"Domain Generalization for Robust Model-Based Offline Reinforcement Learning","created":"2022-11-27","cited_by_count":0,"area":"offlinerl"},{"id":"2211.15065","title":"State-Aware Proximal Pessimistic Algorithms for Offline Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":"offlinerl"},{"id":"2302.00284","title":"Selective Uncertainty Propagation in Offline RL","created":"2023-02-01","cited_by_count":0,"area":"offlinerl"},{"id":"2307.04927","title":"Probabilistic Counterexample Guidance for Safer Reinforcement Learning (Extended Version)","created":"2023-07-10","cited_by_count":0,"area":null},{"id":"2601.01917","title":"Distorted Distributional Policy Evaluation for Offline Reinforcement Learning","created":"2026-01-05","cited_by_count":0,"area":"offlinerl"},{"id":"2605.15620","title":"Pessimistic Risk-Aware Policy Learning in Contextual Bandits","created":"2026-05-15","cited_by_count":0,"area":null}],"next_cursor":null}