{"total":2580,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912,"area":"alignment"},{"id":"2409.19256","title":"HybridFlow: A Flexible and Efficient RLHF Framework","created":"2024-09-28","cited_by_count":2057,"area":"alignment"},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982,"area":"diffusion"},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662,"area":"offlinerl"},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492,"area":"offlinerl"},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459,"area":"offlinerl"},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447,"area":"alignment"},{"id":"2108.06266","title":"Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning","created":"2021-08-13","cited_by_count":371,"area":null},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302,"area":"alignment"},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"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":"2307.04964","title":"Secrets of RLHF in Large Language Models Part I: PPO","created":"2023-07-11","cited_by_count":229,"area":"alignment"},{"id":"2110.11291","title":"Likelihood Training of Schr\\\"odinger Bridge using Forward-Backward SDEs Theory","created":"2021-10-21","cited_by_count":219,"area":null},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215,"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":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2203.08382","title":"Dual Diffusion Implicit Bridges for Image-to-Image Translation","created":"2022-03-16","cited_by_count":213,"area":"diffusion"},{"id":"2108.05877","title":"DexMV: Imitation Learning for Dexterous Manipulation from Human Videos","created":"2021-08-12","cited_by_count":206,"area":"offlinerl"},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2502.07529","title":"Training Deep Learning Models with Norm-Constrained LMOs","created":"2025-02-11","cited_by_count":192,"area":null},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186,"area":null},{"id":"2410.01679","title":"VinePPO: Refining Credit Assignment in RL Training of LLMs","created":"2024-10-02","cited_by_count":183,"area":null},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2404.03715","title":"Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences","created":"2024-04-04","cited_by_count":178,"area":"alignment"},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162,"area":"offlinerl"},{"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":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2305.20081","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","created":"2023-05-31","cited_by_count":157,"area":"diffusion"},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2509.09674","title":"SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning","created":"2025-09-11","cited_by_count":151,"area":"vla"},{"id":"2401.04056","title":"A Minimaximalist Approach to Reinforcement Learning from Human Feedback","created":"2024-01-08","cited_by_count":144,"area":"alignment"},{"id":"2110.15191","title":"URLB: Unsupervised Reinforcement Learning Benchmark","created":"2021-10-28","cited_by_count":139,"area":null},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2404.11999","title":"Token-level Direct Preference Optimization","created":"2024-04-18","cited_by_count":135,"area":"alignment"},{"id":"2304.13653","title":"Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning","created":"2023-04-26","cited_by_count":133,"area":null},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2201.07443","title":"On the Convergence Rates of Policy Gradient Methods","created":"2022-01-19","cited_by_count":119,"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":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"1901.09387","title":"Imitation Learning from Imperfect Demonstration","created":"2019-01-27","cited_by_count":114,"area":"offlinerl"},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2308.02151","title":"Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization","created":"2023-08-04","cited_by_count":112,"area":"agents"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"1810.00821","title":"Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow","created":"2018-10-01","cited_by_count":105,"area":"offlinerl"},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104,"area":null},{"id":"2101.04233","title":"Independent Policy Gradient Methods for Competitive Reinforcement Learning","created":"2021-01-11","cited_by_count":101,"area":null},{"id":"2507.21053","title":"Flow Matching Policy Gradients","created":"2025-07-28","cited_by_count":99,"area":"diffusion"},{"id":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98,"area":"diffusion"},{"id":"2203.10050","title":"SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning","created":"2022-03-18","cited_by_count":97,"area":"alignment"},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2405.15177","title":"Diffusion Actor-Critic with Entropy Regulator","created":"2024-05-24","cited_by_count":94,"area":"diffusion"},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93,"area":"offlinerl"},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91,"area":"offlinerl"},{"id":"2107.09003","title":"Constraints Penalized Q-learning for Safe Offline Reinforcement Learning","created":"2021-07-19","cited_by_count":91,"area":"offlinerl"},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88,"area":"alignment"},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82,"area":null},{"id":"2204.12490","title":"From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation","created":"2022-04-26","cited_by_count":82,"area":"offlinerl"},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2301.13362","title":"Optimizing DDPM Sampling with Shortcut Fine-Tuning","created":"2023-01-31","cited_by_count":81,"area":"diffusion"},{"id":"2106.02684","title":"Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs","created":"2021-06-04","cited_by_count":80,"area":null},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"area":null},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78,"area":"offlinerl"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"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":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74,"area":"offlinerl"},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"1911.10947","title":"State Alignment-based Imitation Learning","created":"2019-11-21","cited_by_count":73,"area":"offlinerl"}],"next_cursor":"100"}