{"total":144,"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":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427,"area":"offlinerl"},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"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":"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":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2010.11895","title":"What are the Statistical Limits of Offline RL with Linear Function Approximation?","created":"2020-10-22","cited_by_count":136,"area":"offlinerl"},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125,"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":"2202.02446","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","created":"2022-02-05","cited_by_count":111,"area":"offlinerl"},{"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":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"id":"2007.08202","title":"Provably Good Batch Reinforcement Learning Without Great Exploration","created":"2020-07-16","cited_by_count":77,"area":"offlinerl"},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2111.10919","title":"Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation","created":"2021-11-21","cited_by_count":71,"area":"offlinerl"},{"id":"2204.08957","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","created":"2022-04-19","cited_by_count":71,"area":null},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"area":"offlinerl"},{"id":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64,"area":"offlinerl"},{"id":"2202.01741","title":"How to Leverage Unlabeled Data in Offline Reinforcement Learning","created":"2022-02-03","cited_by_count":62,"area":"offlinerl"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2106.06630","title":"Corruption-Robust Offline Reinforcement Learning","created":"2021-06-11","cited_by_count":51,"area":"offlinerl"},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"id":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36,"area":null},{"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":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2007.12315","title":"Bayesian Robust Optimization for Imitation Learning","created":"2020-07-24","cited_by_count":28,"area":"offlinerl"},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","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":"2206.10524","title":"Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control","created":"2022-06-21","cited_by_count":28,"area":null},{"id":"2403.01857","title":"Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences","created":"2024-03-04","cited_by_count":27,"area":"alignment"},{"id":"2202.06450","title":"Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality","created":"2022-02-14","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":"2202.13536","title":"LobsDICE: Offline Learning from Observation via Stationary Distribution Correction Estimation","created":"2022-02-28","cited_by_count":23,"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":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","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":"2206.07989","title":"Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination","created":"2022-06-16","cited_by_count":21,"area":"offlinerl"},{"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":"2211.00164","title":"Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information","created":"2022-10-31","cited_by_count":16,"area":"offlinerl"},{"id":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14,"area":"offlinerl"},{"id":"2211.01052","title":"Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints","created":"2022-11-02","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":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2202.09673","title":"A Behavior Regularized Implicit Policy for Offline Reinforcement Learning","created":"2022-02-19","cited_by_count":11,"area":"offlinerl"},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2102.06961","title":"PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators","created":"2021-02-13","cited_by_count":10,"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":"2203.12786","title":"Bellman Residual Orthogonalization for Offline Reinforcement Learning","created":"2022-03-24","cited_by_count":10,"area":"offlinerl"},{"id":"2201.05433","title":"Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning","created":"2022-01-14","cited_by_count":9,"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":"2302.06884","title":"Conservative State Value Estimation for Offline Reinforcement Learning","created":"2023-02-14","cited_by_count":9,"area":"offlinerl"},{"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":"2512.03973","title":"Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning","created":"2025-12-03","cited_by_count":9,"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":"2112.00950","title":"Quantile Filtered Imitation Learning","created":"2021-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-07-06","cited_by_count":6,"area":"offlinerl"},{"id":"2502.13022","title":"Efficient and Sharp Off-Policy Learning under Unobserved Confounding","created":"2025-02-18","cited_by_count":6,"area":null},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2109.14727","title":"Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates","created":"2021-09-29","cited_by_count":5,"area":null},{"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":"2601.23219","title":"MonoScale: Scaling Multi-Agent System with Monotonic Improvement","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2605.23989","title":"Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security","created":"2026-05-17","cited_by_count":5,"area":"agents"},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","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":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","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":"2401.00629","title":"Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning","created":"2024-01-01","cited_by_count":4,"area":"offlinerl"},{"id":"2403.07933","title":"Corruption-Robust Offline Two-Player Zero-Sum Markov Games","created":"2024-03-04","cited_by_count":4,"area":null},{"id":"2109.07275","title":"DROMO: Distributionally Robust Offline Model-based Policy Optimization","created":"2021-09-15","cited_by_count":3,"area":"offlinerl"},{"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":"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":"2308.11267","title":"Robust Lagrangian and Adversarial Policy Gradient for Robust Constrained Markov Decision Processes","created":"2023-08-22","cited_by_count":3,"area":null},{"id":"2310.17245","title":"CROP: Conservative Reward for Model-based Offline Policy Optimization","created":"2023-10-26","cited_by_count":3,"area":"offlinerl"},{"id":"2510.12312","title":"Deep SPI: Safe Policy Improvement via World Models","created":"2025-10-14","cited_by_count":3,"area":"wm"},{"id":"2512.23694","title":"Bellman Calibration for $V$-Learning in Offline Reinforcement Learning","created":"2025-12-29","cited_by_count":3,"area":"offlinerl"},{"id":"2609.22819","title":"Counterfactual Tool Ranking under Utility, Cost, and Privilege Constraints","created":"2026-09-19","cited_by_count":3,"area":null},{"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":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"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":"2111.08066","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning","created":"2021-11-15","cited_by_count":2,"area":"offlinerl"},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2209.04265","title":"Route Planning for Last-Mile Deliveries Using Mobile Parcel Lockers: A Hybrid Q-Learning Network Approach","created":"2022-09-09","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":"2404.00940","title":"Sequential Decision-Making under Uncertainty: A Robust MDPs review","created":"2024-04-01","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}