{"total":46,"rows":[{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"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":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52,"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":"2203.07368","title":"The Efficacy of Pessimism in Asynchronous Q-Learning","created":"2022-03-14","cited_by_count":42,"area":null},{"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":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"id":"2201.03522","title":"When is Offline Two-Player Zero-Sum Markov Game Solvable?","created":"2022-01-10","cited_by_count":28,"area":null},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","cited_by_count":24,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"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":"2310.03173","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","created":"2023-10-04","cited_by_count":17,"area":null},{"id":"2210.01907","title":"A Self-Play Posterior Sampling Algorithm for Zero-Sum Markov Games","created":"2022-10-04","cited_by_count":16,"area":null},{"id":"2305.19001","title":"High-probability sample complexities for policy evaluation with linear function approximation","created":"2023-05-30","cited_by_count":16,"area":null},{"id":"2403.11574","title":"Offline Multitask Representation Learning for Reinforcement Learning","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2302.03319","title":"Leveraging Demonstrations to Improve Online Learning: Quality Matters","created":"2023-02-07","cited_by_count":13,"area":null},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"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":"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":"2206.08364","title":"Interaction-Grounded Learning with Action-inclusive Feedback","created":"2022-06-16","cited_by_count":7,"area":null},{"id":"2110.07510","title":"Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2207.06147","title":"A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2306.06265","title":"Near-optimal Conservative Exploration in Reinforcement Learning under Episode-wise Constraints","created":"2023-06-09","cited_by_count":5,"area":null},{"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":"2607.01111","title":"FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2210.04946","title":"Reaching Goals is Hard: Settling the Sample Complexity of the Stochastic Shortest Path","created":"2022-10-10","cited_by_count":4,"area":null},{"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":"2206.04921","title":"Offline Stochastic Shortest Path: Learning, Evaluation and Towards Optimality","created":"2022-06-10","cited_by_count":3,"area":null},{"id":"2310.11531","title":"Efficient Online Learning with Offline Datasets for Infinite Horizon MDPs: A Bayesian Approach","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2504.03804","title":"Offline and Distributional Reinforcement Learning for Wireless Communications","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2505.13768","title":"Augmenting Online RL with Offline Data is All You Need: A Unified Hybrid RL Algorithm Design and Analysis","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2605.09214","title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","created":"2026-05-09","cited_by_count":3,"area":null},{"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":"2306.11271","title":"Warm-Start Actor-Critic: From Approximation Error to Sub-optimality Gap","created":"2023-06-20","cited_by_count":2,"area":null},{"id":"2409.03996","title":"Goal-Reaching Policy Learning from Non-Expert Observations via Effective Subgoal Guidance","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2501.06339","title":"On The Statistical Complexity of Offline Decision-Making","created":"2025-01-10","cited_by_count":2,"area":null},{"id":"2505.10861","title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2210.13396","title":"Offline congestion games: How feedback type affects data coverage requirement","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2302.05534","title":"Robust Knowledge Transfer in Tiered Reinforcement Learning","created":"2023-02-10","cited_by_count":1,"area":null},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2109.05604","title":"Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies","created":"2021-09-12","cited_by_count":0,"area":null},{"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":"2409.19829","title":"Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2601.21713","title":"Disentangling perception and reasoning for improving data efficiency in learning cloth manipulation without demonstrations","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2605.10289","title":"Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift","created":"2026-05-11","cited_by_count":0,"area":null}],"next_cursor":null}