{"total":111,"rows":[{"id":"2301.11270","title":"Principled Reinforcement Learning with Human Feedback from Pairwise or $K$-wise Comparisons","created":"2023-01-26","cited_by_count":247,"area":"alignment"},{"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":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87,"area":null},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2210.04157","title":"The Role of Coverage in Online Reinforcement Learning","created":"2022-10-09","cited_by_count":83,"area":"offlinerl"},{"id":"2405.19316","title":"Robust Preference Optimization through Reward Model Distillation","created":"2024-05-29","cited_by_count":67,"area":"alignment"},{"id":"2305.14816","title":"Provable Offline Preference-Based Reinforcement Learning","created":"2023-05-24","cited_by_count":55,"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":"2403.03185","title":"Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking","created":"2024-03-05","cited_by_count":50,"area":"alignment"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"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":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32,"area":"offlinerl"},{"id":"2211.11349","title":"Data-Driven Offline Decision-Making via Invariant Representation Learning","created":"2022-11-21","cited_by_count":31,"area":null},{"id":"2302.11048","title":"Adversarial Model for Offline Reinforcement Learning","created":"2023-02-21","cited_by_count":31,"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":"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":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2212.00124","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","created":"2022-11-30","cited_by_count":23,"area":"offlinerl"},{"id":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"area":"offlinerl"},{"id":"2211.13208","title":"On Instance-Dependent Bounds for Offline Reinforcement Learning with Linear Function Approximation","created":"2022-11-23","cited_by_count":22,"area":"offlinerl"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2306.03286","title":"Survival Instinct in Offline Reinforcement Learning","created":"2023-06-05","cited_by_count":20,"area":"offlinerl"},{"id":"2311.08935","title":"Supported Trust Region Optimization for Offline Reinforcement Learning","created":"2023-11-15","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":"2303.17156","title":"MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations","created":"2023-03-30","cited_by_count":18,"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":"2305.12944","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","created":"2023-05-22","cited_by_count":17,"area":"offlinerl"},{"id":"2410.19400","title":"Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression","created":"2024-10-25","cited_by_count":17,"area":"offlinerl"},{"id":"2211.00539","title":"Dungeons and Data: A Large-Scale NetHack Dataset","created":"2022-11-01","cited_by_count":16,"area":"offlinerl"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2402.03807","title":"SEABO: A Simple Search-Based Method for Offline Imitation Learning","created":"2024-02-06","cited_by_count":14,"area":"offlinerl"},{"id":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2301.12714","title":"Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning","created":"2023-01-30","cited_by_count":13,"area":"offlinerl"},{"id":"2304.04660","title":"Uncertainty-driven Trajectory Truncation for Data Augmentation in Offline Reinforcement Learning","created":"2023-04-10","cited_by_count":13,"area":"offlinerl"},{"id":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"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":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2408.08441","title":"D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning","created":"2024-08-15","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":"2306.00321","title":"Improving Offline RL by Blending Heuristics","created":"2023-06-01","cited_by_count":10,"area":"offlinerl"},{"id":"2510.04088","title":"Offline Reinforcement Learning in Large State Spaces: Algorithms and Guarantees","created":"2025-10-05","cited_by_count":10,"area":"offlinerl"},{"id":"2211.04538","title":"ARMOR: A Model-based Framework for Improving Arbitrary Baseline Policies with Offline Data","created":"2022-11-08","cited_by_count":9,"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":"2310.01380","title":"Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning","created":"2023-10-02","cited_by_count":9,"area":"offlinerl"},{"id":"2310.07747","title":"Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples","created":"2023-10-11","cited_by_count":9,"area":"offlinerl"},{"id":"2312.03991","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","created":"2023-12-07","cited_by_count":9,"area":"offlinerl"},{"id":"2410.14069","title":"Rethinking Optimal Transport in Offline Reinforcement Learning","created":"2024-10-17","cited_by_count":9,"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":"2305.03360","title":"A Survey on Offline Model-Based Reinforcement Learning","created":"2023-05-05","cited_by_count":7,"area":"offlinerl"},{"id":"2306.01157","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding","created":"2023-06-01","cited_by_count":7,"area":"offlinerl"},{"id":"2401.03301","title":"On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond","created":"2024-01-06","cited_by_count":6,"area":"offlinerl"},{"id":"2410.15698","title":"Solving Continual Offline RL through Selective Weights Activation on Aligned Spaces","created":"2024-10-21","cited_by_count":6,"area":"offlinerl"},{"id":"2411.00610","title":"Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation","created":"2024-11-01","cited_by_count":6,"area":"offlinerl"},{"id":"2502.08021","title":"Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol","created":"2025-02-11","cited_by_count":6,"area":"offlinerl"},{"id":"2502.08259","title":"Balancing optimism and pessimism in offline-to-online learning","created":"2025-02-12","cited_by_count":6,"area":"offlinerl"},{"id":"2302.03770","title":"Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability","created":"2023-02-07","cited_by_count":5,"area":"offlinerl"},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2403.09701","title":"A Natural Extension To Online Algorithms For Hybrid RL With Limited Coverage","created":"2024-03-07","cited_by_count":5,"area":null},{"id":"2505.20556","title":"Learning a Pessimistic Reward Model in RLHF","created":"2025-05-26","cited_by_count":5,"area":"alignment"},{"id":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","cited_by_count":4,"area":"offlinerl"},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2401.09680","title":"Tiny Multi-Agent DRL for Twins Migration in UAV Metaverses: A Multi-Leader Multi-Follower Stackelberg Game Approach","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2402.09695","title":"Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learning","created":"2024-02-15","cited_by_count":4,"area":"offlinerl"},{"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":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"id":"2605.02141","title":"On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization","created":"2026-05-04","cited_by_count":4,"area":null},{"id":"2309.02157","title":"Model-based Offline Policy Optimization with Adversarial Network","created":"2023-09-05","cited_by_count":3,"area":"offlinerl"},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"id":"2312.02355","title":"When is Offline Policy Selection Sample Efficient for Reinforcement Learning?","created":"2023-12-04","cited_by_count":3,"area":"offlinerl"},{"id":"2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","created":"2025-06-14","cited_by_count":3,"area":"deeprl"},{"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":"2406.04088","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning","created":"2024-06-06","cited_by_count":2,"area":"offlinerl"},{"id":"2412.00086","title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","created":"2024-11-27","cited_by_count":2,"area":"deeprl"},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2504.01719","title":"Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning","created":"2025-04-02","cited_by_count":2,"area":"offlinerl"},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2305.12679","title":"Offline Reinforcement Learning with Additional Covering Distributions","created":"2023-05-22","cited_by_count":1,"area":"offlinerl"},{"id":"2309.16188","title":"Stackelberg Batch Policy Learning","created":"2023-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2402.06102","title":"Real-World Fluid Directed Rigid Body Control via Deep Reinforcement Learning","created":"2024-02-08","cited_by_count":1,"area":"deeprl"},{"id":"2406.10445","title":"Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning","created":"2024-06-14","cited_by_count":1,"area":"alignment"},{"id":"2408.07753","title":"How to Solve Contextual Goal-Oriented Problems with Offline Datasets?","created":"2024-08-14","cited_by_count":1,"area":null},{"id":"2505.17506","title":"Offline Constrained Reinforcement Learning under Partial Data Coverage","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2509.06201","title":"Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control","created":"2025-09-07","cited_by_count":1,"area":null},{"id":"2510.05526","title":"Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment","created":"2025-10-07","cited_by_count":1,"area":"alignment"},{"id":"2603.19987","title":"Breaking the Capability Ceiling of LLM Post-Training by Reintroducing Markov States","created":"2026-03-20","cited_by_count":1,"area":"alignment"},{"id":"2605.01778","title":"Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2304.00573","title":"Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning","created":"2023-04-02","cited_by_count":0,"area":null},{"id":"2309.16631","title":"Robust Offline Reinforcement Learning -- Certify the Confidence Interval","created":"2023-09-28","cited_by_count":0,"area":"offlinerl"},{"id":"2401.00330","title":"Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions","created":"2023-12-30","cited_by_count":0,"area":null}],"next_cursor":"100"}