{"total":83,"rows":[{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"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":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"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":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2402.17135","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","created":"2024-02-27","cited_by_count":31,"area":"deeprl"},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","cited_by_count":29,"area":null},{"id":"2412.08542","title":"MaestroMotif: Skill Design from Artificial Intelligence Feedback","created":"2024-12-11","cited_by_count":24,"area":null},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","created":"2023-06-26","cited_by_count":23,"area":null},{"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":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2402.08530","title":"A Distributional Analogue to the Successor Representation","created":"2024-02-13","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":"2410.18076","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","created":"2024-10-23","cited_by_count":13,"area":null},{"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":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2310.10833","title":"Proper Laplacian Representation Learning","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"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":"2402.13037","title":"Align Your Intents: Offline Imitation Learning via Optimal Transport","created":"2024-02-20","cited_by_count":8,"area":"offlinerl"},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"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":"2507.05477","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":"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":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2510.20264","title":"Optimistic Task Inference for Behavior Foundation Models","created":"2025-10-23","cited_by_count":6,"area":"deeprl"},{"id":"2402.06590","title":"Predictive representations: building blocks of intelligence","created":"2024-02-09","cited_by_count":4,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","created":"2025-05-22","cited_by_count":4,"area":"deeprl"},{"id":"2309.03710","title":"A State Representation for Diminishing Rewards","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2311.16996","title":"Goal-conditioned Offline Planning from Curious Exploration","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2410.08751","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","created":"2024-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2502.10790","title":"Which Features are Best for Successor Features?","created":"2025-02-15","cited_by_count":3,"area":"deeprl"},{"id":"2503.07988","title":"Provable Zero-Shot Generalization in Offline Reinforcement Learning","created":"2025-03-11","cited_by_count":3,"area":"offlinerl"},{"id":"2509.10656","title":"Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration","created":"2025-09-12","cited_by_count":3,"area":null},{"id":"2512.00961","title":"Goal-Driven Reward by Video Diffusion Models for Reinforcement Learning","created":"2025-11-30","cited_by_count":3,"area":"diffusion"},{"id":"2602.06769","title":"Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities","created":"2026-02-06","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":"2505.00787","title":"Constructing an Optimal Behavior Basis for the Option Keyboard","created":"2025-05-01","cited_by_count":2,"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":"2603.02008","title":"Temporal Representations for Exploration: Learning Complex Exploratory Behavior without Extrinsic Rewards","created":"2026-03-02","cited_by_count":2,"area":"deeprl"},{"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":"2310.13391","title":"Learning Successor Features with Distributed Hebbian Temporal Memory","created":"2023-10-20","cited_by_count":1,"area":null},{"id":"2404.07826","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2405.07223","title":"Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning","created":"2024-05-12","cited_by_count":1,"area":"offlinerl"},{"id":"2408.08812","title":"TRAM: Test-Time Risk Adaptation with Mixture of Agents","created":"2024-08-16","cited_by_count":1,"area":"agents"},{"id":"2506.01623","title":"MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer","created":"2025-06-02","cited_by_count":1,"area":"lr"},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","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":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"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":"2604.25496","title":"Improving Zero-Shot Offline RL via Behavioral Task Sampling","created":"2026-04-28","cited_by_count":1,"area":"offlinerl"},{"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":"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":"2407.00744","title":"Disentangled Representations for Causal Cognition","created":"2024-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2502.10792","title":"Tackling the Zero-Shot Reinforcement Learning Loss Directly","created":"2025-02-15","cited_by_count":0,"area":"deeprl"},{"id":"2602.00403","title":"DROGO: Default Representation Objective via Graph Optimization in Reinforcement Learning","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2603.20103","title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","created":"2026-03-20","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":"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":"2605.29906","title":"Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2608.25723","title":"It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learning","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.35615","title":"Behavioral Foundation Models for Quality Diversity","created":"2026-09-28","cited_by_count":0,"area":null},{"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":"2610.02196","title":"InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation","created":"2026-10-01","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":"2610.05350","title":"Task Inference Beyond Least Squares in Behavioral Foundation Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.15429","title":"World Modeling through Spectral Alignment","created":"2026-10-11","cited_by_count":0,"area":"wm"},{"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}