{"total":86,"rows":[{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238,"area":"offlinerl"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2407.01531","title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","created":"2024-07-01","cited_by_count":57,"area":"diffusion"},{"id":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56,"area":"deeprl"},{"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":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2410.20254","title":"Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL","created":"2024-10-26","cited_by_count":21,"area":"deeprl"},{"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":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"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":"2406.06615","title":"Language Guided Skill Discovery","created":"2024-06-07","cited_by_count":16,"area":null},{"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":"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":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","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":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2410.11251","title":"Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning","created":"2024-10-15","cited_by_count":9,"area":"deeprl"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"},{"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":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","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":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6,"area":"deeprl"},{"id":"2410.07877","title":"Constrained Skill Discovery: Quadruped Locomotion with Unsupervised Reinforcement Learning","created":"2024-10-10","cited_by_count":6,"area":"deeprl"},{"id":"2508.08982","title":"Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion","created":"2025-08-12","cited_by_count":6,"area":null},{"id":"2508.13113","title":"Contrastive Representations for Temporal Reasoning","created":"2025-08-18","cited_by_count":6,"area":"lr"},{"id":"2405.03113","title":"Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning","created":"2024-05-06","cited_by_count":5,"area":"deeprl"},{"id":"2502.07279","title":"Exploratory Diffusion Model for Unsupervised Reinforcement Learning","created":"2025-02-11","cited_by_count":5,"area":"diffusion"},{"id":"2603.09036","title":"SCALAR: Learning and Composing Skills through LLM Guided Symbolic Planning and Deep RL Grounding","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2408.12130","title":"S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning","created":"2024-08-22","cited_by_count":4,"area":"deeprl"},{"id":"2507.14748","title":"Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning","created":"2025-07-19","cited_by_count":4,"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":"2402.10820","title":"Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces","created":"2024-02-16","cited_by_count":3,"area":"offlinerl"},{"id":"2406.01641","title":"Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents","created":"2024-06-03","cited_by_count":3,"area":"deeprl"},{"id":"2506.21044","title":"Efficient Skill Discovery via Regret-Aware Optimization","created":"2025-06-26","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":"2603.14245","title":"GoldenStart: Q-Guided Priors and Entropy Control for Distilling Flow Policies","created":"2026-03-15","cited_by_count":3,"area":"diffusion"},{"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":"2406.10127","title":"Exploration by Learning Diverse Skills through Successor State Measures","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2505.04619","title":"Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation","created":"2025-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2509.02930","title":"VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills","created":"2025-09-03","cited_by_count":2,"area":"deeprl"},{"id":"2510.06203","title":"Reference Grounded Skill Discovery","created":"2025-10-07","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":"2605.06145","title":"Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization","created":"2026-05-07","cited_by_count":2,"area":"deeprl"},{"id":"2607.04409","title":"Learning Task-Sufficient World Models by Synergizing Agentic Exploration and Structured Modeling","created":"2026-07-05","cited_by_count":2,"area":"wm"},{"id":"2410.11155","title":"Latent-Predictive Empowerment: Measuring Empowerment without a Simulator","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2501.12668","title":"NBDI: A Simple and Effective Termination Condition for Skill Extraction from Task-Agnostic Demonstrations","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2506.04302","title":"RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming","created":"2025-06-04","cited_by_count":1,"area":"safety"},{"id":"2506.05980","title":"AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2506.09276","title":"Learning The Minimum Action Distance","created":"2025-06-10","cited_by_count":1,"area":null},{"id":"2511.03187","title":"Periodic Skill Discovery","created":"2025-11-05","cited_by_count":1,"area":"deeprl"},{"id":"2602.01619","title":"SUSD: Structured Unsupervised Skill Discovery through State Factorization","created":"2026-02-02","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":"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":"2605.30656","title":"Learning to Perceive the World Through Control: Empowerment-Based Representation Learning","created":"2026-05-28","cited_by_count":1,"area":"deeprl"},{"id":"2606.00950","title":"COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2607.00392","title":"Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL","created":"2026-07-01","cited_by_count":1,"area":"deeprl"},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2411.14085","title":"Exploration by Running Away from the Past","created":"2024-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2506.16718","title":"Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2508.19172","title":"From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2510.04901","title":"Focused Skill Discovery: Learning to Control Specific State Variables while Minimizing Side Effects","created":"2025-10-06","cited_by_count":0,"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":"2601.14000","title":"Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior","created":"2026-01-20","cited_by_count":0,"area":null},{"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":"2604.24127","title":"Leveraging Human Feedback for Semantically-Relevant Skill Discovery","created":"2026-04-27","cited_by_count":0,"area":"alignment"},{"id":"2609.31076","title":"Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2609.36238","title":"ChronoSRL: Temporal Geometry for Self-Supervised Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2609.36691","title":"Video2Skill: From Streaming Experience to Reusable Embodied Skills","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40137","title":"Game-Guided Skill Discovery through Self-Play for Playable Agent Control","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00676","title":"Learning Transferable Skills using Goal-Conditioned Bisimulation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","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":"2610.13002","title":"Scaling Empowered Agents","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17409","title":"Position: Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL","created":"2026-10-12","cited_by_count":0,"area":null},{"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}