{"total":97,"rows":[{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166,"area":"offlinerl"},{"id":"2310.04582","title":"Universal Humanoid Motion Representations for Physics-Based Control","created":"2023-10-06","cited_by_count":116,"area":null},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2104.00683","title":"SimPoE: Simulated Character Control for 3D Human Pose Estimation","created":"2021-04-01","cited_by_count":114,"area":null},{"id":"2305.12411","title":"Synthesizing Diverse Human Motions in 3D Indoor Scenes","created":"2023-05-21","cited_by_count":109,"area":null},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"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":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60,"area":null},{"id":"2112.09251","title":"The Wanderings of Odysseus in 3D Scenes","created":"2021-12-16","cited_by_count":59,"area":null},{"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":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2408.14472","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","created":"2024-08-26","cited_by_count":56,"area":"wm"},{"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":"2309.11351","title":"C$\\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters","created":"2023-09-20","cited_by_count":55,"area":null},{"id":"2402.14606","title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","created":"2024-02-22","cited_by_count":53,"area":"offlinerl"},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2308.15143","title":"Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models","created":"2023-08-29","cited_by_count":37,"area":null},{"id":"2305.04412","title":"Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors","created":"2023-05-08","cited_by_count":36,"area":"driving"},{"id":"2403.12835","title":"AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents","created":"2024-03-19","cited_by_count":32,"area":"offlinerl"},{"id":"2406.00960","title":"PDP: Physics-Based Character Animation via Diffusion Policy","created":"2024-06-03","cited_by_count":31,"area":"diffusion"},{"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":"2407.00187","title":"SMPLOlympics: Sports Environments for Physically Simulated Humanoids","created":"2024-06-28","cited_by_count":29,"area":null},{"id":"2305.03286","title":"Composite Motion Learning with Task Control","created":"2023-05-05","cited_by_count":28,"area":null},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27,"area":"wm"},{"id":"2112.05062","title":"Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies","created":"2021-12-09","cited_by_count":26,"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":"2211.02231","title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","created":"2022-11-04","cited_by_count":24,"area":null},{"id":"2305.19075","title":"Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data","created":"2023-05-30","cited_by_count":20,"area":"offlinerl"},{"id":"2407.16210","title":"Strategy and Skill Learning for Physics-based Table Tennis Animation","created":"2024-07-23","cited_by_count":20,"area":null},{"id":"2103.07084","title":"Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information","created":"2021-03-12","cited_by_count":19,"area":null},{"id":"2104.02180","title":"AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control","created":"2021-04-05","cited_by_count":18,"area":null},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2407.10481","title":"SuperPADL: Scaling Language-Directed Physics-Based Control with Progressive Supervised Distillation","created":"2024-07-15","cited_by_count":17,"area":"deeprl"},{"id":"2408.07295","title":"Learning Multi-Modal Whole-Body Control for Real-World Humanoid Robots","created":"2024-07-30","cited_by_count":16,"area":null},{"id":"2502.05932","title":"Skill Expansion and Composition in Parameter Space","created":"2025-02-09","cited_by_count":14,"area":null},{"id":"2107.03851","title":"Imitation by Predicting Observations","created":"2021-07-08","cited_by_count":13,"area":"offlinerl"},{"id":"2107.05842","title":"Motion Planning by Learning the Solution Manifold in Trajectory Optimization","created":"2021-07-13","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":"2209.12072","title":"Accelerating Reinforcement Learning for Autonomous Driving using Task-Agnostic and Ego-Centric Motion Skills","created":"2022-09-24","cited_by_count":12,"area":"driving"},{"id":"2310.00311","title":"Efficient Planning with Latent Diffusion","created":"2023-09-30","cited_by_count":12,"area":"diffusion"},{"id":"2309.03130","title":"MyoDex: A Generalizable Prior for Dexterous Manipulation","created":"2023-09-06","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":"2112.06061","title":"OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion","created":"2021-12-11","cited_by_count":10,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2205.03943","title":"Learning to Brachiate via Simplified Model Imitation","created":"2022-05-08","cited_by_count":9,"area":null},{"id":"2308.07775","title":"Hierarchical generative modelling for autonomous robots","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2407.15134","title":"Proximal Policy Distillation","created":"2024-07-21","cited_by_count":9,"area":"distill"},{"id":"2505.23708","title":"AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning","created":"2025-05-29","cited_by_count":9,"area":"deeprl"},{"id":"2301.11734","title":"Improving Behavioural Cloning with Positive Unlabeled Learning","created":"2023-01-27","cited_by_count":8,"area":"offlinerl"},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2310.13295","title":"PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2502.14140","title":"ModSkill: Physical Character Skill Modularization","created":"2025-02-19","cited_by_count":7,"area":"offlinerl"},{"id":"2103.02957","title":"Toward Robust Long Range Policy Transfer","created":"2021-03-04","cited_by_count":6,"area":null},{"id":"2205.01906","title":"ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2211.13743","title":"SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration","created":"2022-11-24","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2502.05641","title":"Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2205.11448","title":"Data augmentation for efficient learning from parametric experts","created":"2022-05-23","cited_by_count":5,"area":"offlinerl"},{"id":"2301.13019","title":"Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies","created":"2023-01-30","cited_by_count":5,"area":"offlinerl"},{"id":"2303.12726","title":"Learning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculum","created":"2023-03-14","cited_by_count":5,"area":null},{"id":"2111.00262","title":"Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner","created":"2021-10-30","cited_by_count":4,"area":null},{"id":"2206.00152","title":"Human-AI Shared Control via Policy Dissection","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2201.05242","title":"Neural Circuit Architectural Priors for Embodied Control","created":"2022-01-13","cited_by_count":3,"area":null},{"id":"2201.08115","title":"Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning","created":"2022-01-20","cited_by_count":3,"area":null},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2306.04161","title":"Bidirectional GaitNet: A Bidirectional Prediction Model of Human Gait and Anatomical Conditions","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2411.14913","title":"Enhancing Exploration with Diffusion Policies in Hybrid Off-Policy RL: Application to Non-Prehensile Manipulation","created":"2024-11-22","cited_by_count":3,"area":"diffusion"},{"id":"2503.12814","title":"Versatile Physics-based Character Control with Hybrid Latent Representation","created":"2025-03-17","cited_by_count":3,"area":null},{"id":"2512.24100","title":"Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation","created":"2025-12-30","cited_by_count":3,"area":null},{"id":"2606.31958","title":"Adapting Generalist Robot Policies with Semantic Reinforcement Learning","created":"2026-06-30","cited_by_count":3,"area":"vla"},{"id":"2410.07174","title":"Neural Circuit Architectural Priors for Quadruped Locomotion","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2508.08269","title":"emg2tendon: From sEMG Signals to Tendon Control in Musculoskeletal Hands","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2510.01858","title":"Compositional meta-learning through probabilistic task inference","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2511.20532","title":"MIMIC-MJX: Neuromechanical Emulation of Animal Behavior","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2606.29148","title":"GPC: Large-Scale Generative Pretraining for Transferable Motor Control","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2302.11917","title":"Diverse Policy Optimization for Structured Action Space","created":"2023-02-23","cited_by_count":1,"area":"alignment"},{"id":"2305.17623","title":"On the Value of Myopic Behavior in Policy Reuse","created":"2023-05-28","cited_by_count":1,"area":null},{"id":"2405.11457","title":"Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice","created":"2024-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2407.11915","title":"Imitation of human motion achieves natural head movements for humanoid robots in an active-speaker detection task","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2501.17077","title":"Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning","created":"2025-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2510.06988","title":"No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts","created":"2025-10-08","cited_by_count":1,"area":"diffusion"},{"id":"2603.11346","title":"Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2608.01851","title":"Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2204.13678","title":"Unified Simulation, Perception, and Generation of Human Behavior","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2302.14451","title":"Hierarchical Reinforcement Learning in Complex 3D Environments","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2309.16299","title":"CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture","created":"2023-09-28","cited_by_count":0,"area":"offlinerl"},{"id":"2311.07822","title":"A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2406.04323","title":"ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories","created":"2024-06-06","cited_by_count":0,"area":"deeprl"},{"id":"2408.03525","title":"Hierarchical learning control for autonomous robots inspired by central nervous system","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2601.19411","title":"Task-Centric Policy Optimization from Misaligned Motion Priors","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2606.20705","title":"MotionPyramid: Hierarchical Motion Representation and Residual Interfaces","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.24083","title":"Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.07746","title":"LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation","created":"2026-08-07","cited_by_count":0,"area":"wm"},{"id":"2608.23258","title":"Progressively Learning Heterogeneous Skills in a Unified Latent Space","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.37677","title":"Learning Expressive and Compositional Motion Representation via Spectral Skills","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}