{"total":151,"rows":[{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2208.06193","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","created":"2022-08-12","cited_by_count":562,"area":"diffusion"},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"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":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2209.14548","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","created":"2022-09-29","cited_by_count":182,"area":"offlinerl"},{"id":"2305.20081","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","created":"2023-05-31","cited_by_count":157,"area":"diffusion"},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"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":"2410.13816","title":"Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance","created":"2024-10-17","cited_by_count":106,"area":"vla"},{"id":"2309.16984","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","created":"2023-09-29","cited_by_count":100,"area":"diffusion"},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"area":"offlinerl"},{"id":"2405.15177","title":"Diffusion Actor-Critic with Entropy Regulator","created":"2024-05-24","cited_by_count":94,"area":"diffusion"},{"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":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74,"area":"offlinerl"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2307.11620","title":"Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization","created":"2023-07-21","cited_by_count":43,"area":"offlinerl"},{"id":"2307.04726","title":"Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning","created":"2023-07-10","cited_by_count":42,"area":"diffusion"},{"id":"2301.12842","title":"Direct Preference-based Policy Optimization without Reward Modeling","created":"2023-01-30","cited_by_count":36,"area":"alignment"},{"id":"2402.02439","title":"DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching","created":"2024-02-04","cited_by_count":36,"area":"offlinerl"},{"id":"2302.14372","title":"The In-Sample Softmax for Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":33,"area":"offlinerl"},{"id":"2405.20555","title":"Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning","created":"2024-05-31","cited_by_count":33,"area":"diffusion"},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2304.09853","title":"Bridging RL Theory and Practice with the Effective Horizon","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2110.07395","title":"Offline Reinforcement Learning with Soft Behavior Regularization","created":"2021-10-14","cited_by_count":28,"area":"offlinerl"},{"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":"2309.05915","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","created":"2023-09-12","cited_by_count":25,"area":"offlinerl"},{"id":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"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":"2307.15690","title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","created":"2023-07-28","cited_by_count":23,"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":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21,"area":"offlinerl"},{"id":"2402.00348","title":"ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update","created":"2024-02-01","cited_by_count":21,"area":"offlinerl"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2310.04411","title":"Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL","created":"2023-10-06","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":"2405.18187","title":"AlignIQL: Policy Alignment in Implicit Q-Learning through Constrained Optimization","created":"2024-05-28","cited_by_count":19,"area":"offlinerl"},{"id":"2306.04220","title":"Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL","created":"2023-06-07","cited_by_count":18,"area":"offlinerl"},{"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":"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":"2206.03383","title":"On the Role of Discount Factor in Offline Reinforcement Learning","created":"2022-06-07","cited_by_count":16,"area":"offlinerl"},{"id":"2301.12130","title":"Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2211.15956","title":"Offline Reinforcement Learning with Closed-Form Policy Improvement Operators","created":"2022-11-29","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":"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":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"area":"offlinerl"},{"id":"2212.01105","title":"Flow to Control: Offline Reinforcement Learning with Lossless Primitive Discovery","created":"2022-12-02","cited_by_count":12,"area":"offlinerl"},{"id":"2303.14716","title":"Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning","created":"2023-03-26","cited_by_count":12,"area":"offlinerl"},{"id":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","cited_by_count":12,"area":"deeprl"},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"area":"offlinerl"},{"id":"2411.05193","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","created":"2024-11-07","cited_by_count":10,"area":"offlinerl"},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2303.12206","title":"Policy Optimization for Personalized Interventions in Behavioral Health","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2308.03526","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","created":"2023-08-07","cited_by_count":9,"area":"offlinerl"},{"id":"2401.08819","title":"Learning from Sparse Offline Datasets via Conservative Density Estimation","created":"2024-01-16","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":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2405.14082","title":"Exclusively Penalized Q-learning for Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":8,"area":"offlinerl"},{"id":"2410.01954","title":"ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization","created":"2024-10-02","cited_by_count":8,"area":"offlinerl"},{"id":"2306.08900","title":"Offline Multi-Agent Reinforcement Learning with Coupled Value Factorization","created":"2023-06-15","cited_by_count":7,"area":"offlinerl"},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2312.11935","title":"Parameterized Decision-making with Multi-modal Perception for Autonomous Driving","created":"2023-12-19","cited_by_count":7,"area":"driving"},{"id":"2403.11062","title":"A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization","created":"2024-03-17","cited_by_count":7,"area":"deeprl"},{"id":"2405.11206","title":"Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses","created":"2024-05-18","cited_by_count":7,"area":"offlinerl"},{"id":"2405.12094","title":"Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?","created":"2024-05-20","cited_by_count":7,"area":"ssm"},{"id":"2508.04811","title":"HCRide: Harmonizing Passenger Fairness and Driver Preference for Human-Centered Ride-Hailing","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2112.00950","title":"Quantile Filtered Imitation Learning","created":"2021-12-02","cited_by_count":6,"area":"offlinerl"},{"id":"2306.00972","title":"Improving and Benchmarking Offline Reinforcement Learning Algorithms","created":"2023-06-01","cited_by_count":6,"area":"offlinerl"},{"id":"2306.05412","title":"Decoupled Prioritized Resampling for Offline RL","created":"2023-06-08","cited_by_count":6,"area":"offlinerl"},{"id":"2406.06793","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","created":"2024-06-10","cited_by_count":6,"area":"offlinerl"},{"id":"2502.07237","title":"DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization","created":"2025-02-11","cited_by_count":6,"area":null},{"id":"2210.04251","title":"State Advantage Weighting for Offline RL","created":"2022-10-09","cited_by_count":5,"area":"offlinerl"},{"id":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"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":"2307.06328","title":"Budgeting Counterfactual for Offline RL","created":"2023-07-12","cited_by_count":4,"area":"offlinerl"},{"id":"2405.04307","title":"Improving Offline Reinforcement Learning with Inaccurate Simulators","created":"2024-05-07","cited_by_count":4,"area":"offlinerl"},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2410.20312","title":"Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model","created":"2024-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2510.21995","title":"Is Temporal Difference Learning the Gold Standard for Stitching in RL?","created":"2025-10-24","cited_by_count":4,"area":"deeprl"},{"id":"2201.06468","title":"Chaining Value Functions for Off-Policy Learning","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2302.08865","title":"Swapped goal-conditioned offline reinforcement learning","created":"2023-02-17","cited_by_count":3,"area":"offlinerl"},{"id":"2307.13101","title":"Contrastive Example-Based Control","created":"2023-07-24","cited_by_count":3,"area":null},{"id":"2307.13824","title":"Offline Reinforcement Learning with On-Policy Q-Function Regularization","created":"2023-07-25","cited_by_count":3,"area":"offlinerl"}],"next_cursor":"100"}