{"total":115,"rows":[{"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":"2209.14935","title":"Does Zero-Shot Reinforcement Learning Exist?","created":"2022-09-29","cited_by_count":83,"area":null},{"id":"2304.04782","title":"Reinforcement Learning from Passive Data via Latent Intentions","created":"2023-04-10","cited_by_count":68,"area":null},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"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":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2212.03319","title":"Understanding Self-Predictive Learning for Reinforcement Learning","created":"2022-12-06","cited_by_count":44,"area":null},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","cited_by_count":36,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2306.05483","title":"On the Importance of Exploration for Generalization in Reinforcement Learning","created":"2023-06-08","cited_by_count":31,"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":"2312.05742","title":"The Generalization Gap in Offline Reinforcement Learning","created":"2023-12-10","cited_by_count":26,"area":"offlinerl"},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"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":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"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":"2401.17173","title":"Zero-Shot Reinforcement Learning via Function Encoders","created":"2024-01-30","cited_by_count":18,"area":"deeprl"},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"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":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2211.02100","title":"Contrastive Value Learning: Implicit Models for Simple Offline RL","created":"2022-11-03","cited_by_count":15,"area":"offlinerl"},{"id":"2406.09738","title":"Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation","created":"2024-06-14","cited_by_count":15,"area":"offlinerl"},{"id":"2206.08736","title":"Generalised Policy Improvement with Geometric Policy Composition","created":"2022-06-17","cited_by_count":13,"area":null},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"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":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11,"area":null},{"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":"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":"2110.15701","title":"Successor Feature Representations","created":"2021-10-29","cited_by_count":6,"area":null},{"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":"2510.16617","title":"MoS-VLA: A Vision-Language-Action Model with One-Shot Skill Adaptation","created":"2025-10-18","cited_by_count":5,"area":"vla"},{"id":"2407.09533","title":"Video Occupancy Models","created":"2024-06-25","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":"2507.13181","title":"Spectral Bellman Method: Unifying Representation and Exploration in RL","created":"2025-07-17","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":"2503.22886","title":"Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models","created":"2025-03-28","cited_by_count":3,"area":"offlinerl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"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":"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":"2302.01399","title":"Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2305.00654","title":"Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition","created":"2023-05-01","cited_by_count":2,"area":null},{"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":"2510.06203","title":"Reference Grounded Skill Discovery","created":"2025-10-07","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":"2603.02008","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":"2607.15163","title":"Scaling Behavior Foundation Model for Humanoid Robots","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2208.13298","title":"Goal-Conditioned Q-Learning as Knowledge Distillation","created":"2022-08-28","cited_by_count":1,"area":"distill"},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"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":"2505.21119","title":"Universal Value-Function Uncertainties","created":"2025-05-27","cited_by_count":1,"area":"offlinerl"},{"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":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2510.17059","title":"Consistent Zero-Shot Imitation with Contrastive Goal Inference","created":"2025-10-20","cited_by_count":1,"area":"offlinerl"},{"id":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"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":"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":"2606.01123","title":"From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning","created":"2026-05-31","cited_by_count":1,"area":"alignment"},{"id":"2606.21173","title":"Inverting the Bellman Equation: From $Q$-Values to World Models","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2606.29980","title":"Exploration and Online Transfer with Behavioral Foundation Models","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2502.10792","title":"Tackling the Zero-Shot Reinforcement Learning Loss Directly","created":"2025-02-15","cited_by_count":0,"area":"deeprl"},{"id":"2505.17830","title":"Imagine Beyond! Distributionally Robust Auto-Encoding for State Space Coverage in Online Reinforcement Learning","created":"2025-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2601.22823","title":"Offline Reinforcement Learning of High-Quality Behaviors Under Robust Style Alignment","created":"2026-01-30","cited_by_count":0,"area":"offlinerl"},{"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":"2602.01665","title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","created":"2026-02-02","cited_by_count":0,"area":null},{"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":"2605.20209","title":"NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control","created":"2026-04-15","cited_by_count":0,"area":"diffusion"}],"next_cursor":"100"}