{"total":91,"rows":[{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657,"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":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2401.10700","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","created":"2024-01-19","cited_by_count":64,"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":"2402.04292","title":"AdaFlow: Imitation Learning with Variance-Adaptive Flow-Based Policies","created":"2024-02-06","cited_by_count":50,"area":"offlinerl"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","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":"2503.09722","title":"The Pitfalls of Imitation Learning when Actions are Continuous","created":"2025-03-12","cited_by_count":26,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"area":"offlinerl"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","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":"2511.13035","title":"One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow","created":"2025-11-17","cited_by_count":18,"area":"offlinerl"},{"id":"2309.12716","title":"H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps","created":"2023-09-22","cited_by_count":17,"area":"offlinerl"},{"id":"2505.08078","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","created":"2025-05-12","cited_by_count":15,"area":"offlinerl"},{"id":"2412.18946","title":"Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning","created":"2024-12-25","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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10,"area":"offlinerl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","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":"2508.06269","title":"OM2P: Offline Multi-Agent Mean-Flow Policy","created":"2025-08-08","cited_by_count":8,"area":"offlinerl"},{"id":"2509.23087","title":"Unleashing Flow Policies with Distributional Critics","created":"2025-09-27","cited_by_count":8,"area":"offlinerl"},{"id":"2512.16911","title":"Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning","created":"2025-12-18","cited_by_count":8,"area":"offlinerl"},{"id":"2407.00898","title":"Residual-MPPI: Online Policy Customization for Continuous Control","created":"2024-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2407.04285","title":"Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling","created":"2024-07-05","cited_by_count":7,"area":"offlinerl"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2505.10442","title":"IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning","created":"2025-05-15","cited_by_count":5,"area":"offlinerl"},{"id":"2505.19923","title":"Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL","created":"2025-05-26","cited_by_count":5,"area":"offlinerl"},{"id":"2510.19495","title":"Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning","created":"2025-10-22","cited_by_count":5,"area":"offlinerl"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"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":"2505.05968","title":"Offline Multi-agent Reinforcement Learning via Sequential Score Decomposition","created":"2025-05-09","cited_by_count":4,"area":"offlinerl"},{"id":"2602.05051","title":"ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation","created":"2026-02-04","cited_by_count":4,"area":"offlinerl"},{"id":"2605.10044","title":"Adaptive Action Chunking via Multi-Chunk Q Value Estimation","created":"2026-05-11","cited_by_count":4,"area":"offlinerl"},{"id":"2605.27079","title":"Trust Region Q Adjoint Matching","created":"2026-05-26","cited_by_count":4,"area":"offlinerl"},{"id":"2606.00350","title":"Drift Q-Learning","created":"2026-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2509.24748","title":"Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption","created":"2025-09-29","cited_by_count":3,"area":"offlinerl"},{"id":"2603.13971","title":"Chunk-Guided Q-Learning","created":"2026-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2609.34575","title":"Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning","created":"2026-09-28","cited_by_count":3,"area":"offlinerl"},{"id":"2401.11630","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","created":"2024-01-21","cited_by_count":2,"area":"offlinerl"},{"id":"2406.08238","title":"Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning","created":"2024-06-12","cited_by_count":2,"area":"offlinerl"},{"id":"2412.14834","title":"Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning","created":"2024-12-19","cited_by_count":2,"area":"offlinerl"},{"id":"2506.17155","title":"Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity","created":"2025-06-20","cited_by_count":2,"area":"offlinerl"},{"id":"2507.09534","title":"Consistency Trajectory Planning: High-Quality and Efficient Trajectory Optimization for Offline Model-Based Reinforcement Learning","created":"2025-07-13","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01457","title":"CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making","created":"2026-05-02","cited_by_count":2,"area":"offlinerl"},{"id":"2605.01663","title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","created":"2026-05-03","cited_by_count":2,"area":"offlinerl"},{"id":"2605.08253","title":"Path-Coupled Bellman Flows for Distributional Reinforcement Learning","created":"2026-05-07","cited_by_count":2,"area":"offlinerl"},{"id":"2605.15603","title":"Offline Reinforcement Learning with Universal Horizon Models","created":"2026-05-15","cited_by_count":2,"area":"offlinerl"},{"id":"2606.10613","title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","created":"2026-06-09","cited_by_count":2,"area":"offlinerl"},{"id":"2608.20909","title":"Decoupling Policy Extraction for Offline Reinforcement Learning","created":"2026-08-21","cited_by_count":2,"area":"offlinerl"},{"id":"2311.15920","title":"A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning","created":"2023-11-27","cited_by_count":1,"area":"offlinerl"},{"id":"2505.12211","title":"Imagination-Limited Q-Learning for Offline Reinforcement Learning","created":"2025-05-18","cited_by_count":1,"area":"offlinerl"},{"id":"2506.14058","title":"Implicit Constraint-Aware Off-Policy Correction for Offline Reinforcement Learning","created":"2025-06-16","cited_by_count":1,"area":"offlinerl"},{"id":"2510.22027","title":"Online Optimization for Offline Safe Reinforcement Learning","created":"2025-10-24","cited_by_count":1,"area":"offlinerl"},{"id":"2603.02650","title":"Improving Diffusion Planners by Self-Supervised Action Gating with Energies","created":"2026-03-03","cited_by_count":1,"area":"offlinerl"},{"id":"2605.08202","title":"Beyond Penalization: Diffusion-based Out-of-Distribution Detection and Selective Regularization in Offline Reinforcement Learning","created":"2026-05-06","cited_by_count":1,"area":"offlinerl"},{"id":"2609.02237","title":"Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL","created":"2026-09-02","cited_by_count":1,"area":"offlinerl"},{"id":"2406.03324","title":"UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning","created":"2024-06-05","cited_by_count":0,"area":"offlinerl"},{"id":"2412.11253","title":"Are Expressive Models Truly Necessary for Offline RL?","created":"2024-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2502.12391","title":"Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL","created":"2025-02-18","cited_by_count":0,"area":"offlinerl"},{"id":"2505.20350","title":"Decision Flow Policy Optimization","created":"2025-05-26","cited_by_count":0,"area":"offlinerl"},{"id":"2510.02695","title":"RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularization","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.03013","title":"Distributional Inverse Reinforcement Learning","created":"2025-10-03","cited_by_count":0,"area":"offlinerl"},{"id":"2510.11877","title":"Robust Adversarial Reinforcement Learning in Stochastic Games via Sequence Modeling","created":"2025-10-13","cited_by_count":0,"area":"offlinerl"},{"id":"2512.01987","title":"Forecasting in Offline Reinforcement Learning for Non-stationary Environments","created":"2025-12-01","cited_by_count":0,"area":"offlinerl"},{"id":"2601.00452","title":"Imitation from Observations with Trajectory-Level Generative Embeddings","created":"2026-01-01","cited_by_count":0,"area":"offlinerl"},{"id":"2602.05323","title":"GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.17632","title":"SMAC: Score-Matched Actor-Critics for Robust Offline-to-Online Transfer","created":"2026-02-19","cited_by_count":0,"area":"offlinerl"},{"id":"2604.12509","title":"Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal Controllers","created":"2026-04-14","cited_by_count":0,"area":"offlinerl"},{"id":"2604.22229","title":"Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning","created":"2026-04-24","cited_by_count":0,"area":"offlinerl"},{"id":"2605.11009","title":"ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network","created":"2026-05-10","cited_by_count":0,"area":"offlinerl"},{"id":"2605.29033","title":"Moment Matching Q-Learning","created":"2026-05-27","cited_by_count":0,"area":"offlinerl"},{"id":"2605.30190","title":"Mean-Field Diffuser: Scaling Offline MARL to Thousands of Agents","created":"2026-05-28","cited_by_count":0,"area":"offlinerl"},{"id":"2607.01225","title":"Language-Critique Imitation Learning from Suboptimal Demonstrations","created":"2026-07-01","cited_by_count":0,"area":"offlinerl"},{"id":"2608.20208","title":"RoMAN-Flow: Taming Autoregressive Normalizing Flows for Offline Reinforcement Learning in Robotic Manipulation","created":"2026-08-20","cited_by_count":0,"area":"offlinerl"},{"id":"2608.23939","title":"CoDrift: Compositional Drifting for Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"},{"id":"2609.19414","title":"Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation","created":"2026-09-16","cited_by_count":0,"area":"offlinerl"},{"id":"2609.24489","title":"Lifted Bellman Linear Programming for Offline Reinforcement Learning","created":"2026-09-21","cited_by_count":0,"area":"offlinerl"},{"id":"2609.29000","title":"Learning from Mixed-Quality Deployment Experience for Robot Manipulation","created":"2026-09-24","cited_by_count":0,"area":"offlinerl"},{"id":"2609.40149","title":"Role-Adaptive Policy Optimization for Offline Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2610.05882","title":"Mulligan: Performance-Guided Data Collection for Efficient On-Robot Learning","created":"2026-10-05","cited_by_count":0,"area":"offlinerl"},{"id":"2610.07899","title":"Variance-Averse $n$-Step Offline Reinforcement Learning for Sparse Long-Horizon Environments","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"},{"id":"2610.08989","title":"LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"},{"id":"2610.11175","title":"Higher-Order Action Supervision Makes A Strong Policy Class","created":"2026-10-08","cited_by_count":0,"area":"offlinerl"},{"id":"2610.16984","title":"From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"offlinerl"},{"id":"2610.20190","title":"Value-Guided Repulsion for Offline Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}