{"total":111,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"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":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"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":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"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":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"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":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"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":"2008.05533","title":"Overcoming Model Bias for Robust Offline Deep Reinforcement Learning","created":"2020-08-12","cited_by_count":43,"area":"offlinerl"},{"id":"2305.01738","title":"Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare","created":"2023-05-02","cited_by_count":42,"area":"offlinerl"},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2203.02638","title":"Safe Reinforcement Learning for Legged Locomotion","created":"2022-03-05","cited_by_count":35,"area":null},{"id":"2206.10442","title":"Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning","created":"2022-06-21","cited_by_count":35,"area":"offlinerl"},{"id":"2103.09575","title":"Regularized Behavior Value Estimation","created":"2021-03-17","cited_by_count":32,"area":"offlinerl"},{"id":"2110.14000","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","created":"2021-10-26","cited_by_count":32,"area":"offlinerl"},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2110.07067","title":"Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement","created":"2021-10-13","cited_by_count":29,"area":"driving"},{"id":"2111.04714","title":"A Dataset Perspective on Offline Reinforcement Learning","created":"2021-11-08","cited_by_count":27,"area":"offlinerl"},{"id":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2110.04156","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","created":"2021-10-08","cited_by_count":24,"area":"offlinerl"},{"id":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2203.09365","title":"Semi-Markov Offline Reinforcement Learning for Healthcare","created":"2022-03-17","cited_by_count":18,"area":"offlinerl"},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"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":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2004.00981","title":"Benchmarking End-to-End Behavioural Cloning on Video Games","created":"2020-04-02","cited_by_count":15,"area":"offlinerl"},{"id":"2006.13189","title":"Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation","created":"2020-06-23","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":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"area":"offlinerl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9,"area":"offlinerl"},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2410.24218","title":"Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use","created":"2024-10-31","cited_by_count":7,"area":"deeprl"},{"id":"2011.14379","title":"Offline Reinforcement Learning Hands-On","created":"2020-11-29","cited_by_count":6,"area":"offlinerl"},{"id":"2012.13682","title":"POPO: Pessimistic Offline Policy Optimization","created":"2020-12-26","cited_by_count":5,"area":"offlinerl"},{"id":"2102.04285","title":"RL-Scope: Cross-Stack Profiling for Deep Reinforcement Learning Workloads","created":"2021-02-08","cited_by_count":5,"area":null},{"id":"2201.02381","title":"Offline Reinforcement Learning for Road Traffic Control","created":"2022-01-07","cited_by_count":5,"area":"offlinerl"},{"id":"2301.13019","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","created":"2023-01-30","cited_by_count":5,"area":"offlinerl"},{"id":"2403.18454","title":"Scaling Vision-and-Language Navigation With Offline RL","created":"2024-03-27","cited_by_count":5,"area":"offlinerl"},{"id":"2408.12136","title":"Provable Domain Adaptation for Offline Reinforcement Learning with Limited Samples","created":"2024-08-22","cited_by_count":5,"area":"offlinerl"},{"id":"2412.04327","title":"Action Mapping for Reinforcement Learning in Continuous Environments with Constraints","created":"2024-12-05","cited_by_count":5,"area":"deeprl"},{"id":"2111.04279","title":"Batch Reinforcement Learning from Crowds","created":"2021-11-08","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":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2104.10258","title":"Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning","created":"2021-04-20","cited_by_count":3,"area":"offlinerl"},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2206.14198","title":"Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning","created":"2022-06-26","cited_by_count":3,"area":null},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2302.08865","title":"Swapped goal-conditioned offline reinforcement learning","created":"2023-02-17","cited_by_count":3,"area":"offlinerl"},{"id":"2305.00905","title":"BCQQ: Batch-Constraint Quantum Q-Learning with Cyclic Data Re-uploading","created":"2023-04-27","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":"2309.16718","title":"A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning","created":"2023-09-13","cited_by_count":3,"area":"offlinerl"},{"id":"2401.01369","title":"RL-MPCA: A Reinforcement Learning Based Multi-Phase Computation Allocation Approach for Recommender Systems","created":"2023-12-27","cited_by_count":3,"area":null},{"id":"2410.23031","title":"Offline Reinforcement Learning and Sequence Modeling for Downlink Link Adaptation","created":"2024-10-30","cited_by_count":3,"area":"offlinerl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2502.02153","title":"Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing","created":"2025-02-04","cited_by_count":3,"area":"alignment"},{"id":"2506.03154","title":"Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RL","created":"2025-05-19","cited_by_count":3,"area":"diffusion"},{"id":"2605.05172","title":"When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for On-Robot Reinforcement Learning","created":"2026-05-06","cited_by_count":3,"area":"offlinerl"},{"id":"2103.08070","title":"Learning robust driving policies without online exploration","created":"2021-03-15","cited_by_count":2,"area":"driving"},{"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":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2302.09605","title":"Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning","created":"2023-02-19","cited_by_count":2,"area":"offlinerl"},{"id":"2306.08044","title":"Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care","created":"2023-06-13","cited_by_count":2,"area":null},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2507.00485","title":"PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning","created":"2025-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2510.12253","title":"Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development","created":"2025-10-14","cited_by_count":2,"area":"diffusion"},{"id":"2607.28226","title":"Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"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":"2212.02620","title":"Benchmarking Offline Reinforcement Learning Algorithms for E-Commerce Order Fraud Evaluation","created":"2022-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.03870","title":"Knowledge Transfer from Teachers to Learners in Growing-Batch Reinforcement Learning","created":"2023-05-05","cited_by_count":1,"area":null},{"id":"2402.09550","title":"Dataset Clustering for Improved Offline Policy Learning","created":"2024-02-14","cited_by_count":1,"area":"offlinerl"},{"id":"2403.00841","title":"Offline Fictitious Self-Play for Competitive Games","created":"2024-02-29","cited_by_count":1,"area":"offlinerl"},{"id":"2406.07041","title":"Integrating Domain Knowledge for handling Limited Data in Offline RL","created":"2024-06-11","cited_by_count":1,"area":"offlinerl"},{"id":"2409.15753","title":"Development and Validation of Heparin Dosing Policies Using an Offline Reinforcement Learning Algorithm","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2511.04147","title":"Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning","created":"2025-11-06","cited_by_count":1,"area":"deeprl"},{"id":"2602.06445","title":"ECO: Energy-Constrained Optimization with Reinforcement Learning for Humanoid Walking","created":"2026-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2605.11694","title":"Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"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":"2108.12916","title":"A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning","created":"2021-08-29","cited_by_count":0,"area":null},{"id":"2109.07380","title":"DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning","created":"2021-09-15","cited_by_count":0,"area":"offlinerl"},{"id":"2111.08817","title":"Compressive Features in Offline Reinforcement Learning for Recommender Systems","created":"2021-11-16","cited_by_count":0,"area":"offlinerl"},{"id":"2202.12578","title":"Learning to Liquidate Forex: Optimal Stopping via Adaptive Top-K Regression","created":"2022-02-25","cited_by_count":0,"area":null},{"id":"2205.09550","title":"Data Valuation for Offline Reinforcement Learning","created":"2022-05-19","cited_by_count":0,"area":"offlinerl"},{"id":"2205.13950","title":"Non-Markovian policies occupancy measures","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2210.11111","title":"The Pump Scheduling Problem: A Real-World Scenario for Reinforcement Learning","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2212.08302","title":"Safe Evaluation For Offline Learning: Are We Ready To Deploy?","created":"2022-12-16","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":"2310.08660","title":"Learning RL-Policies for Joint Beamforming Without Exploration: A Batch Constrained Off-Policy Approach","created":"2023-10-12","cited_by_count":0,"area":null},{"id":"2406.03912","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","created":"2024-06-06","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}