{"total":671,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293,"area":"offlinerl"},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982,"area":"diffusion"},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2208.06193","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","created":"2022-08-12","cited_by_count":562,"area":"diffusion"},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364,"area":"offlinerl"},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325,"area":"diffusion"},{"id":"2409.00588","title":"Diffusion Policy Policy Optimization","created":"2024-09-01","cited_by_count":280,"area":"diffusion"},{"id":"2309.11235","title":"OpenChat: Advancing Open-source Language Models with Mixed-Quality Data","created":"2023-09-20","cited_by_count":252,"area":null},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"2406.11896","title":"DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning","created":"2024-06-14","cited_by_count":214,"area":"mllm"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184,"area":"diffusion"},{"id":"2209.14548","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","created":"2022-09-29","cited_by_count":182,"area":"offlinerl"},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2505.18719","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","created":"2025-05-24","cited_by_count":176,"area":"vla"},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2506.15799","title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","created":"2025-06-18","cited_by_count":169,"area":"diffusion"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"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":"2305.20081","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","created":"2023-05-31","cited_by_count":157,"area":"diffusion"},{"id":"2502.05450","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","created":"2025-02-08","cited_by_count":154,"area":"vla"},{"id":"2304.12824","title":"Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning","created":"2023-04-25","cited_by_count":149,"area":"diffusion"},{"id":"2403.03949","title":"Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation","created":"2024-03-06","cited_by_count":144,"area":"offlinerl"},{"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":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138,"area":"offlinerl"},{"id":"2401.16013","title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","created":"2024-01-29","cited_by_count":136,"area":"deeprl"},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"area":"offlinerl"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"area":"offlinerl"},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119,"area":"offlinerl"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"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":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2410.13816","title":"Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance","created":"2024-10-17","cited_by_count":106,"area":"vla"},{"id":"2302.00935","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","created":"2023-02-02","cited_by_count":104,"area":"offlinerl"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2309.16984","title":"Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning","created":"2023-09-29","cited_by_count":100,"area":"diffusion"},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93,"area":"offlinerl"},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89,"area":"offlinerl"},{"id":"2204.05618","title":"When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?","created":"2022-04-12","cited_by_count":89,"area":"offlinerl"},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2406.09329","title":"Is Value Learning Really the Main Bottleneck in Offline RL?","created":"2024-06-13","cited_by_count":89,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2206.02829","title":"RORL: Robust Offline Reinforcement Learning via Conservative Smoothing","created":"2022-06-06","cited_by_count":84,"area":"offlinerl"},{"id":"2010.14500","title":"COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning","created":"2020-10-27","cited_by_count":83,"area":"offlinerl"},{"id":"2106.03400","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","created":"2021-06-07","cited_by_count":79,"area":"offlinerl"},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79,"area":null},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2210.05178","title":"Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials","created":"2022-10-11","cited_by_count":78,"area":"offlinerl"},{"id":"2511.00091","title":"Self-Improving Vision-Language-Action Models with Data Generation via Residual RL","created":"2025-10-30","cited_by_count":78,"area":"vla"},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76,"area":"offlinerl"},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74,"area":"offlinerl"},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73,"area":"offlinerl"},{"id":"2110.06192","title":"Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapes","created":"2021-10-12","cited_by_count":71,"area":null},{"id":"2412.13630","title":"Policy Decorator: Model-Agnostic Online Refinement for Large Policy Model","created":"2024-12-18","cited_by_count":70,"area":"offlinerl"},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2410.04640","title":"Unpacking Failure Modes of Generative Policies: Runtime Monitoring of Consistency and Progress","created":"2024-10-06","cited_by_count":69,"area":"offlinerl"},{"id":"2305.15363","title":"Inverse Preference Learning: Preference-based RL without a Reward Function","created":"2023-05-24","cited_by_count":68,"area":"alignment"},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"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":"2311.02198","title":"Imitation Bootstrapped Reinforcement Learning","created":"2023-11-03","cited_by_count":64,"area":"offlinerl"},{"id":"2412.07762","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","created":"2024-12-10","cited_by_count":63,"area":"offlinerl"},{"id":"2212.05698","title":"MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations","created":"2022-12-12","cited_by_count":62,"area":null},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2510.14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning","created":"2025-10-16","cited_by_count":59,"area":"deeprl"},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2312.14134","title":"Diffusion Reward: Learning Rewards via Conditional Video Diffusion","created":"2023-12-21","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":"2404.16660","title":"Benchmarking Mobile Device Control Agents across Diverse Configurations","created":"2024-04-25","cited_by_count":55,"area":"agents"},{"id":"2509.19301","title":"Residual Off-Policy RL for Finetuning Behavior Cloning Policies","created":"2025-09-23","cited_by_count":55,"area":null},{"id":"2202.04628","title":"Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration","created":"2022-02-09","cited_by_count":54,"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":"2409.16578","title":"FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning","created":"2024-09-25","cited_by_count":54,"area":"deeprl"},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53,"area":"offlinerl"},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"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":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50,"area":"offlinerl"},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"area":"offlinerl"},{"id":"2210.05492","title":"Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning","created":"2022-10-11","cited_by_count":48,"area":null}],"next_cursor":"100"}