{"total":240,"rows":[{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141,"area":null},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133,"area":null},{"id":"2206.08686","title":"Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning","created":"2022-06-17","cited_by_count":119,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2211.08416","title":"Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment","created":"2022-11-15","cited_by_count":108,"area":null},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"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":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"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":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"area":null},{"id":"2310.15145","title":"Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning","created":"2023-10-23","cited_by_count":54,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"area":null},{"id":"2306.00942","title":"Train Offline, Test Online: A Real Robot Learning Benchmark","created":"2023-06-01","cited_by_count":47,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42,"area":null},{"id":"2204.13060","title":"Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning","created":"2022-04-27","cited_by_count":38,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","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":"2507.07986","title":"EXPO: Stable Reinforcement Learning with Expressive Policies","created":"2025-07-10","cited_by_count":34,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2205.08129","title":"Planning to Practice: Efficient Online Fine-Tuning by Composing Goals in Latent Space","created":"2022-05-17","cited_by_count":31,"area":null},{"id":"2407.07788","title":"BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark","created":"2024-07-10","cited_by_count":30,"area":null},{"id":"2207.04703","title":"Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learning","created":"2022-07-11","cited_by_count":29,"area":null},{"id":"2412.10798","title":"AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games","created":"2024-12-14","cited_by_count":28,"area":null},{"id":"2210.06601","title":"Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Tasks","created":"2022-10-12","cited_by_count":25,"area":null},{"id":"2302.06604","title":"ALAN: Autonomously Exploring Robotic Agents in the Real World","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2206.09674","title":"EAGER: Asking and Answering Questions for Automatic Reward Shaping in Language-guided RL","created":"2022-06-20","cited_by_count":23,"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":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22,"area":null},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2211.11802","title":"Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning","created":"2022-11-21","cited_by_count":20,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2310.01737","title":"Blending Imitation and Reinforcement Learning for Robust Policy Improvement","created":"2023-10-03","cited_by_count":17,"area":null},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2412.14584","title":"Simulation-Free Hierarchical Latent Policy Planning for Proactive Dialogues","created":"2024-12-19","cited_by_count":14,"area":null},{"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":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2303.01076","title":"Hallucinated Adversarial Control for Conservative Offline Policy Evaluation","created":"2023-03-02","cited_by_count":13,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2405.17879","title":"Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree","created":"2024-05-28","cited_by_count":13,"area":null},{"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":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2210.02343","title":"Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning","created":"2022-10-05","cited_by_count":11,"area":null},{"id":"2312.02682","title":"H-GAP: Humanoid Control with a Generalist Planner","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2401.05442","title":"Functional Graphical Models: Structure Enables Offline Data-Driven Optimization","created":"2024-01-08","cited_by_count":11,"area":null},{"id":"2303.06121","title":"Ignorance is Bliss: Robust Control via Information Gating","created":"2023-03-10","cited_by_count":10,"area":null},{"id":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2302.02477","title":"Offline Learning of Closed-Loop Deep Brain Stimulation Controllers for Parkinson Disease Treatment","created":"2023-02-05","cited_by_count":8,"area":null},{"id":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"area":null},{"id":"2401.03137","title":"SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning","created":"2024-01-06","cited_by_count":8,"area":null},{"id":"2403.06328","title":"Distributional Successor Features Enable Zero-Shot Policy Optimization","created":"2024-03-10","cited_by_count":8,"area":null},{"id":"2502.11918","title":"VLP: Vision-Language Preference Learning for Embodied Manipulation","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2503.21200","title":"Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation","created":"2025-03-27","cited_by_count":8,"area":null},{"id":"2505.14903","title":"When to retrain a machine learning model","created":"2025-05-20","cited_by_count":8,"area":null},{"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":"2505.01396","title":"SIME: Enhancing Policy Self-Improvement with Modal-level Exploration","created":"2025-05-02","cited_by_count":7,"area":null},{"id":"2307.12425","title":"On the Effectiveness of Offline RL for Dialogue Response Generation","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2407.16680","title":"A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data","created":"2024-07-23","cited_by_count":6,"area":null},{"id":"2412.17018","title":"GAS: Generative Auto-bidding with Post-training Search","created":"2024-12-22","cited_by_count":6,"area":null},{"id":"2509.19292","title":"SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration","created":"2025-09-23","cited_by_count":6,"area":null},{"id":"2306.13944","title":"Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery","created":"2023-06-24","cited_by_count":5,"area":null},{"id":"2307.04887","title":"Measuring and Mitigating Interference in Reinforcement Learning","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2311.01331","title":"Offline Imitation from Observation via Primal Wasserstein State Occupancy Matching","created":"2023-11-02","cited_by_count":5,"area":null},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2509.03348","title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2602.06939","title":"Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2607.01111","title":"FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement","created":"2026-07-01","cited_by_count":5,"area":null},{"id":"2304.00354","title":"On Context Distribution Shift in Task Representation Learning for Offline Meta RL","created":"2023-04-01","cited_by_count":4,"area":null},{"id":"2307.11373","title":"Offline Diversity Maximization Under Imitation Constraints","created":"2023-07-21","cited_by_count":4,"area":null},{"id":"2402.02186","title":"Evolution Guided Generative Flow Networks","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2405.05861","title":"ExACT: An End-to-End Autonomous Excavator System Using Action Chunking With Transformers","created":"2024-05-09","cited_by_count":4,"area":null},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2504.13368","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2601.18175","title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success","created":"2026-01-26","cited_by_count":4,"area":null}],"next_cursor":"100"}