{"total":126,"rows":[{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2506.15799","title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","created":"2025-06-18","cited_by_count":169,"area":"diffusion"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"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":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"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":"2312.12044","title":"XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX","created":"2023-12-19","cited_by_count":55,"area":null},{"id":"2601.14234","title":"Q-learning with Adjoint Matching","created":"2026-01-20","cited_by_count":37,"area":"diffusion"},{"id":"2401.09750","title":"Exploration and Anti-Exploration with Distributional Random Network Distillation","created":"2024-01-18","cited_by_count":33,"area":"deeprl"},{"id":"2406.18043","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","created":"2024-06-26","cited_by_count":31,"area":"wm"},{"id":"2505.22866","title":"Scaling Offline RL via Efficient and Expressive Shortcut Models","created":"2025-05-28","cited_by_count":27,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2411.07934","title":"Doubly Mild Generalization for Offline Reinforcement Learning","created":"2024-11-12","cited_by_count":21,"area":"offlinerl"},{"id":"2502.04778","title":"Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning","created":"2025-02-07","cited_by_count":20,"area":"diffusion"},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2505.08078","title":"What Matters for Batch Online Reinforcement Learning in Robotics?","created":"2025-05-12","cited_by_count":15,"area":"offlinerl"},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"area":"deeprl"},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13,"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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2511.05005","title":"Multi-agent Coordination via Flow Matching","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"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":"2602.01439","title":"TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse","created":"2026-02-01","cited_by_count":9,"area":"deeprl"},{"id":"2602.13810","title":"Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation","created":"2026-02-14","cited_by_count":9,"area":"deeprl"},{"id":"2507.08761","title":"Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data","created":"2025-07-11","cited_by_count":7,"area":"deeprl"},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"id":"2605.13435","title":"Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy","created":"2026-05-13","cited_by_count":6,"area":"deeprl"},{"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":"2306.08772","title":"Katakomba: Tools and Benchmarks for Data-Driven NetHack","created":"2023-06-14","cited_by_count":5,"area":"offlinerl"},{"id":"2407.12163","title":"Bellman Diffusion Models","created":"2024-07-16","cited_by_count":5,"area":"diffusion"},{"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":"2601.10471","title":"DeFlow: Decoupling Manifold Modeling and Value Maximization for Offline Policy Extraction","created":"2026-01-15","cited_by_count":5,"area":"diffusion"},{"id":"2604.14265","title":"Reinforcement Learning via Value Gradient Flow","created":"2026-04-15","cited_by_count":5,"area":"offlinerl"},{"id":"2403.13097","title":"Simple Ingredients for Offline Reinforcement Learning","created":"2024-03-19","cited_by_count":4,"area":"offlinerl"},{"id":"2406.06309","title":"Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?","created":"2024-06-10","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":"2506.09574","title":"MOORL: A Framework for Integrating Offline-Online Reinforcement Learning","created":"2025-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2510.01460","title":"The Three Regimes of Offline-to-Online Reinforcement Learning","created":"2025-10-01","cited_by_count":4,"area":"offlinerl"},{"id":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","cited_by_count":4,"area":"deeprl"},{"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":"2606.00350","title":"Drift Q-Learning","created":"2026-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2402.01812","title":"Distilling LLMs' Decomposition Abilities into Compact Language Models","created":"2024-02-02","cited_by_count":3,"area":"lr"},{"id":"2404.16399","title":"Offline Reinforcement Learning with Behavioral Supervisor Tuning","created":"2024-04-25","cited_by_count":3,"area":"offlinerl"},{"id":"2408.02165","title":"SelfBC: Self Behavior Cloning for Offline Reinforcement Learning","created":"2024-08-04","cited_by_count":3,"area":"offlinerl"},{"id":"2501.06700","title":"Average Reward Reinforcement Learning for Wireless Radio Resource Management","created":"2025-01-12","cited_by_count":3,"area":"deeprl"},{"id":"2602.09580","title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2603.13971","title":"Chunk-Guided Q-Learning","created":"2026-03-14","cited_by_count":3,"area":"offlinerl"},{"id":"2605.07727","title":"Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2605.26552","title":"Aligning Few-Step Generative Models by Amortizing Sample-based Variational Inference","created":"2026-05-26","cited_by_count":3,"area":null},{"id":"2606.14801","title":"QPILOTS: Efficient Test-Time Q-Steering for Flow Policies","created":"2026-06-11","cited_by_count":3,"area":"diffusion"},{"id":"2409.02724","title":"Surgical Task Automation Using Actor-Critic Frameworks and Self-Supervised Imitation Learning","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2409.07606","title":"The Role of Deep Learning Regularizations on Actors in Offline RL","created":"2024-09-11","cited_by_count":2,"area":"offlinerl"},{"id":"2410.22728","title":"Offline Behavior Distillation","created":"2024-10-30","cited_by_count":2,"area":"deeprl"},{"id":"2511.02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","created":"2025-11-04","cited_by_count":2,"area":"offlinerl"},{"id":"2602.02847","title":"Causal Flow Q-Learning for Robust Offline Reinforcement Learning","created":"2026-02-02","cited_by_count":2,"area":"diffusion"},{"id":"2603.04333","title":"What Does Flow Matching Bring To TD Learning?","created":"2026-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2603.08399","title":"A Recipe for Stable Offline Multi-agent Reinforcement Learning","created":"2026-03-09","cited_by_count":2,"area":"offlinerl"},{"id":"2604.17919","title":"Fisher Decorator: Refining Flow Policy via a Local Transport Map","created":"2026-04-20","cited_by_count":2,"area":"diffusion"},{"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":"2605.06156","title":"Entropy-Regularized Adjoint Matching for Offline Reinforcement Learning","created":"2026-05-07","cited_by_count":2,"area":"diffusion"},{"id":"2605.11151","title":"RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Ranking","created":"2026-05-11","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":"2605.22711","title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-21","cited_by_count":2,"area":"offlinerl"},{"id":"2606.17551","title":"Reversal Q-Learning","created":"2026-06-16","cited_by_count":2,"area":"diffusion"},{"id":"2406.04534","title":"Strategically Conservative Q-Learning","created":"2024-06-06","cited_by_count":1,"area":"offlinerl"},{"id":"2408.10713","title":"Offline Model-Based Reinforcement Learning with Anti-Exploration","created":"2024-08-20","cited_by_count":1,"area":"offlinerl"},{"id":"2501.18138","title":"B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning","created":"2025-01-30","cited_by_count":1,"area":"offlinerl"},{"id":"2502.06584","title":"Alert: Learning Trigger Functions for Early Classification of Time Series using Deep-RL","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2506.00131","title":"Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimization","created":"2025-05-30","cited_by_count":1,"area":"offlinerl"},{"id":"2506.08644","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2507.02356","title":"Offline Reinforcement Learning with Penalized Action Noise Injection","created":"2025-07-03","cited_by_count":1,"area":"diffusion"},{"id":"2507.10843","title":"Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps","created":"2025-07-14","cited_by_count":1,"area":"offlinerl"},{"id":"2508.19900","title":"Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning","created":"2025-08-27","cited_by_count":1,"area":"offlinerl"},{"id":"2509.24067","title":"In-Context Compositional Q-Learning for Offline Reinforcement Learning","created":"2025-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2510.01105","title":"Geometric Analysis of Neural Regression Collapse via Intrinsic Dimension","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2511.08922","title":"Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning","created":"2025-11-12","cited_by_count":1,"area":"diffusion"},{"id":"2512.04341","title":"Long-Horizon Model-Based Offline Reinforcement Learning Without Explicit Conservatism","created":"2025-12-04","cited_by_count":1,"area":"offlinerl"},{"id":"2512.06692","title":"State Diversity Matters in Offline Behavior Distillation","created":"2025-12-07","cited_by_count":1,"area":"offlinerl"},{"id":"2602.05776","title":"Cross-Domain Offline Policy Adaptation via Selective Transition Correction","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2602.07441","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","created":"2026-02-07","cited_by_count":1,"area":"offlinerl"},{"id":"2603.22430","title":"Inference Time Policy Optimization for Offline RL with Differentiable World Models","created":"2026-03-23","cited_by_count":1,"area":"wm"},{"id":"2605.01968","title":"AdamO: A Collapse-Suppressed Optimizer for Offline RL","created":"2026-05-03","cited_by_count":1,"area":"offlinerl"},{"id":"2605.12416","title":"Aligning Flow Map Policies with Optimal Q-Guidance","created":"2026-05-12","cited_by_count":1,"area":"diffusion"},{"id":"2609.06882","title":"Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement Learning","created":"2026-09-07","cited_by_count":1,"area":"diffusion"},{"id":"2406.13376","title":"Efficient Offline Reinforcement Learning: First Imitate, then Improve","created":"2024-06-19","cited_by_count":0,"area":"offlinerl"},{"id":"2508.04225","title":"Symmetric Behavior Regularized Policy Optimization","created":"2025-08-06","cited_by_count":0,"area":"offlinerl"},{"id":"2508.05960","title":"Mildly Conservative Regularized Evaluation for Offline Reinforcement Learning","created":"2025-08-08","cited_by_count":0,"area":"offlinerl"},{"id":"2509.10303","title":"Generalizing Beyond Suboptimality: Offline Reinforcement Learning Learns Effective Scheduling through Random Solutions","created":"2025-09-12","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":"2510.25205","title":"Energy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision","created":"2025-10-29","cited_by_count":0,"area":"driving"}],"next_cursor":"100"}