{"total":375,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327,"area":null},{"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":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"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":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2412.18194","title":"VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks","created":"2024-12-24","cited_by_count":175,"area":"lr"},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2307.04738","title":"RoCo: Dialectic Multi-Robot Collaboration with Large Language Models","created":"2023-07-10","cited_by_count":172,"area":null},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2310.12567","title":"Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark","created":"2023-10-19","cited_by_count":143,"area":null},{"id":"2303.07280","title":"Vision-Language Models as Success Detectors","created":"2023-03-13","cited_by_count":142,"area":"mllm"},{"id":"2312.11752","title":"Learning a Diffusion Model Policy from Rewards via Q-Score Matching","created":"2023-12-18","cited_by_count":138,"area":"diffusion"},{"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":"2310.01557","title":"SmartPlay: A Benchmark for LLMs as Intelligent Agents","created":"2023-10-02","cited_by_count":125,"area":"agents"},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123,"area":null},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112,"area":null},{"id":"2102.09430","title":"State Entropy Maximization with Random Encoders for Efficient Exploration","created":"2021-02-18","cited_by_count":108,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2111.03026","title":"B-Pref: Benchmarking Preference-Based Reinforcement Learning","created":"2021-11-04","cited_by_count":106,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","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":"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":"2012.11547","title":"Offline Reinforcement Learning from Images with Latent Space Models","created":"2020-12-21","cited_by_count":95,"area":"offlinerl"},{"id":"2209.04899","title":"Instruction-driven history-aware policies for robotic manipulations","created":"2022-09-11","cited_by_count":94,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2212.03363","title":"Few-Shot Preference Learning for Human-in-the-Loop RL","created":"2022-12-06","cited_by_count":87,"area":null},{"id":"2208.07860","title":"A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning","created":"2022-08-16","cited_by_count":83,"area":"wm"},{"id":"2111.12083","title":"VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles","created":"2021-11-23","cited_by_count":81,"area":null},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"area":null},{"id":"2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control","created":"2021-03-03","cited_by_count":77,"area":null},{"id":"2104.06303","title":"Learning and Planning in Complex Action Spaces","created":"2021-04-13","cited_by_count":77,"area":null},{"id":"2406.08474","title":"Real2Code: Reconstruct Articulated Objects via Code Generation","created":"2024-06-12","cited_by_count":69,"area":null},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","cited_by_count":68,"area":"wm"},{"id":"2312.09187","title":"Vision-Language Models as a Source of Rewards","created":"2023-12-14","cited_by_count":66,"area":"mllm"},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"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":"2202.03825","title":"skrl: Modular and Flexible Library for Reinforcement Learning","created":"2022-02-08","cited_by_count":49,"area":null},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48,"area":null},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44,"area":null},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2506.09981","title":"ReSim: Reliable World Simulation for Autonomous Driving","created":"2025-06-11","cited_by_count":44,"area":"wm"},{"id":"2210.13383","title":"Evaluating Long-Term Memory in 3D Mazes","created":"2022-10-24","cited_by_count":43,"area":null},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null},{"id":"2310.06343","title":"Boosting Continuous Control with Consistency Policy","created":"2023-10-10","cited_by_count":38,"area":"diffusion"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2310.02054","title":"AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model","created":"2023-10-03","cited_by_count":37,"area":"diffusion"},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","cited_by_count":36,"area":null},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34,"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":"2311.02496","title":"LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion","created":"2023-11-04","cited_by_count":33,"area":"offlinerl"},{"id":"2305.16985","title":"Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation","created":"2023-05-26","cited_by_count":31,"area":null},{"id":"2406.18043","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","created":"2024-06-26","cited_by_count":31,"area":"wm"},{"id":"2509.25756","title":"SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling","created":"2025-09-30","cited_by_count":31,"area":"deeprl"},{"id":"2201.12427","title":"Towards Safe Reinforcement Learning with a Safety Editor Policy","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2203.17138","title":"Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors","created":"2022-03-31","cited_by_count":30,"area":null},{"id":"2304.04150","title":"RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning","created":"2023-04-09","cited_by_count":30,"area":null},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30,"area":"offlinerl"},{"id":"2209.11221","title":"Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2407.00187","title":"SMPLOlympics: Sports Environments for Physically Simulated Humanoids","created":"2024-06-28","cited_by_count":29,"area":null},{"id":"2106.13229","title":"Model-Based Reinforcement Learning via Latent-Space Collocation","created":"2021-06-24","cited_by_count":28,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2307.10224","title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","created":"2023-07-15","cited_by_count":28,"area":null},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2111.01365","title":"Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics","created":"2021-11-02","cited_by_count":27,"area":"offlinerl"},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2305.14133","title":"Conditional Mutual Information for Disentangled Representations in Reinforcement Learning","created":"2023-05-23","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2105.07253","title":"Regret Minimization Experience Replay in Off-Policy Reinforcement Learning","created":"2021-05-15","cited_by_count":25,"area":null},{"id":"2109.10781","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","created":"2021-09-22","cited_by_count":25,"area":null},{"id":"2208.07363","title":"MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control","created":"2022-08-15","cited_by_count":25,"area":null},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2210.12566","title":"Solving Continuous Control via Q-learning","created":"2022-10-22","cited_by_count":24,"area":null},{"id":"2301.11774","title":"Reinforcement Learning from Diverse Human Preferences","created":"2023-01-27","cited_by_count":24,"area":"alignment"},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24,"area":"wm"},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2305.19476","title":"Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2202.09982","title":"Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"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":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null}],"next_cursor":"100"}