{"total":56,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"id":"2503.14858","title":"1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities","created":"2025-03-19","cited_by_count":45,"area":"deeprl"},{"id":"2509.20478","title":"Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations","created":"2025-09-24","cited_by_count":24,"area":"offlinerl"},{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16,"area":"deeprl"},{"id":"2502.05454","title":"Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following","created":"2025-02-08","cited_by_count":14,"area":null},{"id":"2505.23527","title":"Normalizing Flows are Capable Models for Continuous Control","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","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":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2511.07730","title":"Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning","created":"2025-11-11","cited_by_count":8,"area":"deeprl"},{"id":"2608.09853","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","created":"2026-08-10","cited_by_count":7,"area":"alignment"},{"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":"2508.13113","title":"Contrastive Representations for Temporal Reasoning","created":"2025-08-18","cited_by_count":6,"area":"lr"},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"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":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2509.23802","title":"STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning","created":"2025-09-28","cited_by_count":3,"area":"alignment"},{"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":"2608.30640","title":"Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL","created":"2026-08-31","cited_by_count":3,"area":"deeprl"},{"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":"2512.07976","title":"VLD: Visual Language Goal Distance for Reinforcement Learning Navigation","created":"2025-12-08","cited_by_count":2,"area":"deeprl"},{"id":"2604.08960","title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","created":"2026-04-10","cited_by_count":2,"area":"offlinerl"},{"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":"2508.05535","title":"Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation","created":"2025-08-07","cited_by_count":1,"area":null},{"id":"2510.17059","title":"Consistent Zero-Shot Imitation with Contrastive Goal Inference","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2603.22273","title":"Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration","created":"2026-03-23","cited_by_count":1,"area":"deeprl"},{"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":"2607.00392","title":"Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL","created":"2026-07-01","cited_by_count":1,"area":"deeprl"},{"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":"2610.07796","title":"The Geometry of Empowerment","created":"2026-10-06","cited_by_count":1,"area":null},{"id":"2512.24827","title":"Inter-Agent Relative Representations for Multi-Agent Option Discovery","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2604.00686","title":"Full-Gradient Successor Feature Representations","created":"2026-04-01","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":"2605.01865","title":"Quality-Aware Exploration Budget Allocation for Cooperative Multi-Agent Reinforcement Learning","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.13207","title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.04188","title":"Dual Advantage Fields","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"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":"2607.27422","title":"Good Rankers, Bad Objectives: Bilinear Contrastive Critics under Expressive Policy Search","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.03875","title":"Enhancing VLM Reward Models Through Structure-Aware Fine-Tuning","created":"2026-08-04","cited_by_count":0,"area":"alignment"},{"id":"2608.29061","title":"PathBridger: Subgoal Bridges for Offline Goal-Conditioned Reinforcement Learning","created":"2026-08-29","cited_by_count":0,"area":"offlinerl"},{"id":"2609.08642","title":"SUN: Reaching for Novelty in Reinforcement Learning","created":"2026-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2609.33259","title":"GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences","created":"2026-09-27","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":"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":"2610.05087","title":"Direction-Conditioned Policies for Online Goal-Conditioned Reinforcement Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.20009","title":"Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}