{"total":53,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"1910.01708","title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","created":"2019-10-03","cited_by_count":111,"area":"offlinerl"},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73,"area":"offlinerl"},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2212.10439","title":"Policy Gradient in Robust MDPs with Global Convergence Guarantee","created":"2022-12-20","cited_by_count":38,"area":null},{"id":"2007.12315","title":"Bayesian Robust Optimization for Imitation Learning","created":"2020-07-24","cited_by_count":28,"area":"offlinerl"},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2106.00099","title":"Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs","created":"2021-05-31","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":"2411.11451","title":"Robust Markov Decision Processes: A Place Where AI and Formal Methods Meet","created":"2024-11-18","cited_by_count":18,"area":null},{"id":"2308.10797","title":"Stabilizing Unsupervised Environment Design with a Learned Adversary","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2211.00863","title":"Behavior Prior Representation learning for Offline Reinforcement Learning","created":"2022-11-02","cited_by_count":12,"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":"2312.13912","title":"Solving Long-run Average Reward Robust MDPs via Stochastic Games","created":"2023-12-21","cited_by_count":10,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2305.07958","title":"More for Less: Safe Policy Improvement With Stronger Performance Guarantees","created":"2023-05-13","cited_by_count":9,"area":"offlinerl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2201.12175","title":"Safe Policy Improvement Approaches on Discrete Markov Decision Processes","created":"2022-01-28","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":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2404.05424","title":"What Are the Odds? Improving the foundations of Statistical Model Checking","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2203.06587","title":"Policy Learning for Robust Markov Decision Process with a Mismatched Generative Model","created":"2022-03-13","cited_by_count":4,"area":null},{"id":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"id":"2309.08925","title":"DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning","created":"2023-09-16","cited_by_count":4,"area":"offlinerl"},{"id":"2406.00274","title":"A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes","created":"2024-06-01","cited_by_count":4,"area":"deeprl"},{"id":"2110.15907","title":"Learning to Be Cautious","created":"2021-10-29","cited_by_count":3,"area":null},{"id":"2209.09446","title":"A Joint Imitation-Reinforcement Learning Framework for Reduced Baseline Regret","created":"2022-09-20","cited_by_count":3,"area":null},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2105.05473","title":"Interpretable performance analysis towards offline reinforcement learning: A dataset perspective","created":"2021-05-12","cited_by_count":2,"area":"offlinerl"},{"id":"2404.00940","title":"Sequential Decision-Making under Uncertainty: A Robust MDPs review","created":"2024-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2408.12004","title":"CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2410.09361","title":"Decision-Point Guided Safe Policy Improvement","created":"2024-10-12","cited_by_count":2,"area":"offlinerl"},{"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":"2507.15532","title":"Data-Efficient Safe Policy Improvement Using Parametric Structure","created":"2025-07-21","cited_by_count":2,"area":"offlinerl"},{"id":"2605.10293","title":"Robust Probabilistic Shielding for Safe Offline Reinforcement Learning","created":"2026-05-11","cited_by_count":2,"area":"offlinerl"},{"id":"2109.09034","title":"Greedy UnMixing for Q-Learning in Multi-Agent Reinforcement Learning","created":"2021-09-19","cited_by_count":1,"area":null},{"id":"2208.00724","title":"Safe Policy Improvement Approaches and their Limitations","created":"2022-08-01","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":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2407.13006","title":"Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":null},{"id":"2503.03885","title":"Seldonian Reinforcement Learning for Ad Hoc Teamwork","created":"2025-03-05","cited_by_count":1,"area":"offlinerl"},{"id":"2105.13431","title":"An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes","created":"2021-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2212.13819","title":"Don't do it: Safer Reinforcement Learning With Rule-based Guidance","created":"2022-12-28","cited_by_count":0,"area":null},{"id":"2305.19035","title":"Solving Robust MDPs through No-Regret Dynamics","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","cited_by_count":0,"area":null},{"id":"2404.05055","title":"Percentile Criterion Optimization in Offline Reinforcement Learning","created":"2024-04-07","cited_by_count":0,"area":"offlinerl"},{"id":"2510.19672","title":"Policy Learning with Abstention","created":"2025-10-22","cited_by_count":0,"area":null},{"id":"2608.24986","title":"Solving Robust POMDPs with Omega-regular Objectives via Partially Observable Stochastic Games","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2609.39106","title":"Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain Baselines","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}