{"total":1099,"rows":[{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348,"area":null},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942,"area":null},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876,"area":"agents"},{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323,"area":"lr"},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316,"area":"alignment"},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237,"area":"wm"},{"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":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182,"area":null},{"id":"2304.02948","title":"FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead","created":"2023-04-06","cited_by_count":175,"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":"2310.08710","title":"Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research","created":"2023-10-12","cited_by_count":160,"area":"wm"},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2504.07934","title":"SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement","created":"2025-04-10","cited_by_count":145,"area":"lr"},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143,"area":null},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2404.07965","title":"Rho-1: Not All Tokens Are What You Need","created":"2024-04-11","cited_by_count":133,"area":null},{"id":"2208.01893","title":"Flow Annealed Importance Sampling Bootstrap","created":"2022-08-03","cited_by_count":127,"area":null},{"id":"2303.07507","title":"Loss of Plasticity in Continual Deep Reinforcement Learning","created":"2023-03-13","cited_by_count":121,"area":null},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"area":"lr"},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2206.07632","title":"Exploring Chemical Space with Score-based Out-of-distribution Generation","created":"2022-06-06","cited_by_count":95,"area":null},{"id":"2104.06294","title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","created":"2021-04-13","cited_by_count":90,"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":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84,"area":"lr"},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2305.07170","title":"Towards Understanding and Improving GFlowNet Training","created":"2023-05-11","cited_by_count":75,"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":"2202.03091","title":"Auto-Lambda: Disentangling Dynamic Task Relationships","created":"2022-02-07","cited_by_count":73,"area":null},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72,"area":null},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71,"area":null},{"id":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2110.01219","title":"Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation","created":"2021-10-04","cited_by_count":68,"area":null},{"id":"2410.14803","title":"DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents","created":"2024-10-18","cited_by_count":68,"area":"lr"},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"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":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"id":"2311.11908","title":"Continual Learning: Applications and the Road Forward","created":"2023-11-20","cited_by_count":59,"area":null},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2101.06521","title":"Hierarchical Reinforcement Learning By Discovering Intrinsic Options","created":"2021-01-16","cited_by_count":58,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"area":null},{"id":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"area":null},{"id":"2308.05384","title":"Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization","created":"2023-08-10","cited_by_count":56,"area":"diffusion"},{"id":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55,"area":null},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"2111.11032","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","created":"2021-11-22","cited_by_count":49,"area":null},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2506.06698","title":"Contextual Experience Replay for Self-Improvement of Language Agents","created":"2025-06-07","cited_by_count":48,"area":"agents"},{"id":"2507.05386","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","created":"2025-07-07","cited_by_count":47,"area":null},{"id":"2201.01601","title":"FedBalancer: Data and Pace Control for Efficient Federated Learning on Heterogeneous Clients","created":"2022-01-05","cited_by_count":46,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"area":null},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2310.16029","title":"Finetuning Offline World Models in the Real World","created":"2023-10-24","cited_by_count":41,"area":"wm"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2507.07451","title":"RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning","created":"2025-07-10","cited_by_count":39,"area":"lr"},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"1907.04543","title":"An Optimistic Perspective on Offline Reinforcement Learning","created":"2019-07-10","cited_by_count":37,"area":"offlinerl"},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37,"area":null},{"id":"2202.12513","title":"TeachAugment: Data Augmentation Optimization Using Teacher Knowledge","created":"2022-02-25","cited_by_count":37,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"1809.02064","title":"Sample-Efficient Imitation Learning via Generative Adversarial Nets","created":"2018-09-06","cited_by_count":36,"area":"offlinerl"},{"id":"2106.12059","title":"Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning","created":"2021-06-22","cited_by_count":36,"area":null},{"id":"2203.12710","title":"The Challenges of Continuous Self-Supervised Learning","created":"2022-03-23","cited_by_count":36,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2101.00531","title":"Context-Aware Safe Reinforcement Learning for Non-Stationary Environments","created":"2021-01-02","cited_by_count":33,"area":null},{"id":"2108.12081","title":"Detection and Continual Learning of Novel Face Presentation Attacks","created":"2021-08-27","cited_by_count":33,"area":null},{"id":"2211.09231","title":"The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry","created":"2022-11-16","cited_by_count":33,"area":null},{"id":"2309.06599","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","created":"2023-09-12","cited_by_count":33,"area":"diffusion"},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33,"area":null},{"id":"2103.09575","title":"Regularized Behavior Value Estimation","created":"2021-03-17","cited_by_count":32,"area":"offlinerl"},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2205.13323","title":"The Effect of Task Ordering in Continual Learning","created":"2022-05-26","cited_by_count":31,"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":"2311.12495","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","created":"2023-11-21","cited_by_count":31,"area":null},{"id":"2103.16409","title":"Deep Hedging of Derivatives Using Reinforcement Learning","created":"2021-03-29","cited_by_count":30,"area":null},{"id":"2410.06508","title":"Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning","created":"2024-10-09","cited_by_count":30,"area":"lr"},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2103.01948","title":"Offline Reinforcement Learning with Pseudometric Learning","created":"2021-03-02","cited_by_count":28,"area":"offlinerl"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null}],"next_cursor":"100"}