{"total":94,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"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":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2501.10105","title":"Universal Actions for Enhanced Embodied Foundation Models","created":"2025-01-17","cited_by_count":82,"area":null},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57,"area":"offlinerl"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2604.03208","title":"Hierarchical Planning with Latent World Models","created":"2026-04-03","cited_by_count":43,"area":"wm"},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2505.12737","title":"Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning","created":"2025-05-19","cited_by_count":23,"area":"offlinerl"},{"id":"2510.00739","title":"TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning","created":"2025-10-01","cited_by_count":22,"area":"deeprl"},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"id":"2601.00844","title":"Value-guided action planning with JEPA world models","created":"2025-12-28","cited_by_count":21,"area":"wm"},{"id":"2411.19418","title":"Proto Successor Measure: Representing the Behavior Space of an RL Agent","created":"2024-11-29","cited_by_count":20,"area":"deeprl"},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"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":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13,"area":"diffusion"},{"id":"2602.18639","title":"Learning Invariant Visual Representations for Planning with Joint-Embedding Predictive World Models","created":"2026-02-20","cited_by_count":13,"area":"wm"},{"id":"2412.04368","title":"Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting","created":"2024-12-05","cited_by_count":12,"area":"offlinerl"},{"id":"2506.07744","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","created":"2025-06-09","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":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2411.07007","title":"Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching","created":"2024-11-11","cited_by_count":10,"area":"offlinerl"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2505.13150","title":"Zero-Shot Adaptation of Behavioral Foundation Models to Unseen Dynamics","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2507.12496","title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","created":"2025-07-15","cited_by_count":8,"area":"wm"},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"id":"2412.05718","title":"RLZero: Direct Policy Inference from Language Without In-Domain Supervision","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2510.15382","title":"Towards Robust Zero-Shot Reinforcement Learning","created":"2025-10-17","cited_by_count":7,"area":"deeprl"},{"id":"2602.19634","title":"Compositional Planning with Jumpy World Models","created":"2026-02-23","cited_by_count":7,"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":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2510.08218","title":"Expressive Value Learning for Scalable Offline Reinforcement Learning","created":"2025-10-09","cited_by_count":6,"area":"diffusion"},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2506.18847","title":"Offline Goal-Conditioned Reinforcement Learning with Projective Quasimetric Planning","created":"2025-06-23","cited_by_count":5,"area":"offlinerl"},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2601.21233","title":"Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs","created":"2026-01-29","cited_by_count":4,"area":"agents"},{"id":"2408.01384","title":"NOLO: Navigate Only Look Once","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","cited_by_count":3,"area":"deeprl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2409.17992","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","created":"2024-09-26","cited_by_count":2,"area":"deeprl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2509.25550","title":"Unifying Agent Interaction and World Information for Multi-agent Coordination","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.01962","title":"Zero-Shot Off-Policy Learning","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.15857","title":"Regularized Latent Dynamics Prediction is a Strong Baseline For Behavioral Foundation Models","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.24532","title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","created":"2026-04-27","cited_by_count":2,"area":"deeprl"},{"id":"2605.03075","title":"Refining Compositional Diffusion for Reliable Long-Horizon Planning","created":"2026-05-04","cited_by_count":2,"area":null},{"id":"2607.07855","title":"NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2506.09276","title":"Learning The Minimum Action Distance","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2506.15190","title":"Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2601.22496","title":"Action-Sufficient Goal Representations","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.07730","title":"The Laplacian Keyboard: Beyond the Linear Span","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.25464","title":"Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning","created":"2026-03-26","cited_by_count":1,"area":"deeprl"},{"id":"2604.05931","title":"Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning","created":"2026-04-07","cited_by_count":1,"area":"deeprl"},{"id":"2604.20627","title":"Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning","created":"2026-04-22","cited_by_count":1,"area":"wm"},{"id":"2605.06470","title":"Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies","created":"2026-05-07","cited_by_count":1,"area":"offlinerl"},{"id":"2605.20609","title":"Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"offlinerl"},{"id":"2605.25740","title":"Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning","created":"2026-05-25","cited_by_count":1,"area":"offlinerl"},{"id":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2609.02322","title":"What Is Worth Representing? Representational Empowerment for Continual Model Construction","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2406.01377","title":"Multi-Agent Transfer Learning via Temporal Contrastive Learning","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2510.17531","title":"Plasma Shape Control via Zero-shot Generative Reinforcement Learning","created":"2025-10-20","cited_by_count":0,"area":"deeprl"},{"id":"2601.19452","title":"APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2602.12087","title":"Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RL","created":"2026-02-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.01862","title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","created":"2026-05-03","cited_by_count":0,"area":"ssm"},{"id":"2605.13207","title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.16863","title":"Plan First, Diffuse Later: Extrinsic Graph Guidance for Long-Horizon Diffusion Planning","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2605.17017","title":"When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited","created":"2026-05-16","cited_by_count":0,"area":"offlinerl"},{"id":"2606.06618","title":"ChronoForest: Closed-Loop Multi-Tree Diffusion Planning for Efficient Bridge Search and Route Composition","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.16515","title":"Direction-Conditioned Policies via Compositional Subgoal Scoring for Online Goal-Conditioned Reinforcement Learning","created":"2026-06-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.25389","title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.31016","title":"Robust Successor Features","created":"2026-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2609.32634","title":"PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models","created":"2026-09-26","cited_by_count":0,"area":"vla"},{"id":"2609.35880","title":"From Static Policies to Adaptive Priors in Offline Reinforcement Learning","created":"2026-09-26","cited_by_count":0,"area":"offlinerl"},{"id":"2609.36238","title":"ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.38383","title":"Learning to Plan from Random Exploration","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39901","title":"Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.00676","title":"Learning Transferable Skills using Goal-Conditioned Bisimulation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00778","title":"Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.04988","title":"How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models","created":"2026-10-04","cited_by_count":0,"area":"wm"},{"id":"2610.05087","title":"Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.05350","title":"Task Inference Beyond Least Squares in Behavioral Foundation Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.14400","title":"Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations","created":"2026-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2610.19883","title":"Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}