{"total":118,"rows":[{"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":"2103.14274","title":"Character Controllers Using Motion VAEs","created":"2021-03-26","cited_by_count":184,"area":null},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"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":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"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":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"id":"2104.11203","title":"Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention","created":"2021-04-22","cited_by_count":95,"area":null},{"id":"2203.15103","title":"Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions","created":"2022-03-28","cited_by_count":89,"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":"2107.03996","title":"Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers","created":"2021-07-08","cited_by_count":79,"area":null},{"id":"2104.04644","title":"Fast and Efficient Locomotion via Learned Gait Transitions","created":"2021-04-09","cited_by_count":54,"area":null},{"id":"2111.03062","title":"Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning","created":"2021-11-04","cited_by_count":50,"area":null},{"id":"2308.12517","title":"Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotion","created":"2023-08-24","cited_by_count":47,"area":null},{"id":"2502.10363","title":"BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds","created":"2025-02-14","cited_by_count":46,"area":null},{"id":"2110.10809","title":"Hierarchical Skills for Efficient Exploration","created":"2021-10-20","cited_by_count":38,"area":null},{"id":"2205.12292","title":"Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video","created":"2022-05-24","cited_by_count":37,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"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":"2110.01411","title":"Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey","created":"2021-09-28","cited_by_count":28,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","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":"2109.14549","title":"Vision-Guided Quadrupedal Locomotion in the Wild with Multi-Modal Delay Randomization","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2205.02625","title":"GANimator: Neural Motion Synthesis from a Single Sequence","created":"2022-05-05","cited_by_count":23,"area":null},{"id":"2105.10049","title":"Learning Modular Robot Control Policies","created":"2021-05-20","cited_by_count":22,"area":null},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22,"area":null},{"id":"2305.20065","title":"Latent Exploration for Reinforcement Learning","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2110.01894","title":"Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models","created":"2021-10-05","cited_by_count":20,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2310.00239","title":"AdaptNet: Policy Adaptation for Physics-Based Character Control","created":"2023-09-30","cited_by_count":16,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2602.02473","title":"HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos","created":"2026-02-02","cited_by_count":14,"area":null},{"id":"2201.12044","title":"Generative GaitNet","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2205.00307","title":"Learning to Get Up","created":"2022-04-30","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":"2108.04526","title":"A Survey on Deep Reinforcement Learning for Data Processing and Analytics","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2201.13248","title":"SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulation","created":"2022-01-27","cited_by_count":10,"area":null},{"id":"2305.10997","title":"Sharing Lifelong Reinforcement Learning Knowledge via Modulating Masks","created":"2023-05-18","cited_by_count":10,"area":null},{"id":"2308.02459","title":"Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration","created":"2023-08-04","cited_by_count":9,"area":null},{"id":"2104.02863","title":"The Value of Planning for Infinite-Horizon Model Predictive Control","created":"2021-04-07","cited_by_count":8,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2103.10000","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","created":"2021-03-18","cited_by_count":7,"area":null},{"id":"2103.11775","title":"Measuring and modeling the motor system with machine learning","created":"2021-03-22","cited_by_count":7,"area":null},{"id":"2306.09010","title":"DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control","created":"2023-06-15","cited_by_count":7,"area":null},{"id":"2409.07409","title":"Robust Robot Walker: Learning Agile Locomotion over Tiny Traps","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2110.04357","title":"Training Transition Policies via Distribution Matching for Complex Tasks","created":"2021-10-08","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2310.04676","title":"Surgical Gym: A high-performance GPU-based platform for reinforcement learning with surgical robots","created":"2023-10-07","cited_by_count":6,"area":null},{"id":"2401.08632","title":"Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning","created":"2023-12-10","cited_by_count":6,"area":null},{"id":"2412.13157","title":"Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions","created":"2024-12-17","cited_by_count":6,"area":null},{"id":"2104.12365","title":"Efficient Hyperparameter Optimization for Physics-based Character Animation","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2106.13935","title":"Discovering Generalizable Skills via Automated Generation of Diverse Tasks","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2111.10005","title":"Reinforcement Learning with Adaptive Curriculum Dynamics Randomization for Fault-Tolerant Robot Control","created":"2021-11-19","cited_by_count":5,"area":null},{"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":"2101.09640","title":"Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline","created":"2021-01-24","cited_by_count":4,"area":null},{"id":"2106.01741","title":"Lifetime policy reuse and the importance of task capacity","created":"2021-06-03","cited_by_count":4,"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":"2203.02857","title":"Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations","created":"2022-03-06","cited_by_count":4,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2312.08466","title":"Efficiently Quantifying Individual Agent Importance in Cooperative MARL","created":"2023-12-13","cited_by_count":4,"area":null},{"id":"2602.02331","title":"TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2104.14534","title":"On the Emergence of Whole-body Strategies from Humanoid Robot Push-recovery Learning","created":"2021-04-29","cited_by_count":3,"area":null},{"id":"2107.10901","title":"A reinforcement learning approach to resource allocation in genomic selection","created":"2021-07-22","cited_by_count":3,"area":null},{"id":"2201.05242","title":"Neural Circuit Architectural Priors for Embodied Control","created":"2022-01-13","cited_by_count":3,"area":null},{"id":"2202.07068","title":"Motivating Physical Activity via Competitive Human-Robot Interaction","created":"2022-02-14","cited_by_count":3,"area":null},{"id":"2209.06905","title":"Graph Neural Network Based Node Deployment for Throughput Enhancement","created":"2022-08-19","cited_by_count":3,"area":null},{"id":"2211.06665","title":"A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges","created":"2022-11-12","cited_by_count":3,"area":null},{"id":"2305.04180","title":"Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity","created":"2023-05-07","cited_by_count":3,"area":null},{"id":"2311.02215","title":"Towards model-free RL algorithms that scale well with unstructured data","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2509.12507","title":"Learning to Generate Pointing Gestures in Situated Embodied Conversational Agents","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2101.09391","title":"Learning Setup Policies: Reliable Transition Between Locomotion Behaviours","created":"2021-01-23","cited_by_count":2,"area":null},{"id":"2105.04699","title":"Adaptive Policy Transfer in Reinforcement Learning","created":"2021-05-10","cited_by_count":2,"area":null},{"id":"2107.02955","title":"Quadruped Locomotion on Non-Rigid Terrain using Reinforcement Learning","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2108.06161","title":"Reinforcement Learning for Robot Navigation with Adaptive Forward Simulation Time (AFST) in a Semi-Markov Model","created":"2021-08-13","cited_by_count":2,"area":null},{"id":"2208.02932","title":"Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment","created":"2022-08-04","cited_by_count":2,"area":null},{"id":"2209.02010","title":"On the Origins of Self-Modeling","created":"2022-09-05","cited_by_count":2,"area":null},{"id":"2311.03651","title":"SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations","created":"2023-11-07","cited_by_count":2,"area":null},{"id":"2410.07174","title":"Neural Circuit Architectural Priors for Quadruped Locomotion","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2103.05174","title":"Learning to Play Soccer From Scratch: Sample-Efficient Emergent Coordination through Curriculum-Learning and Competition","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2104.04768","title":"Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms","created":"2021-04-10","cited_by_count":1,"area":null},{"id":"2110.08169","title":"Containerized Distributed Value-Based Multi-Agent Reinforcement Learning","created":"2021-10-15","cited_by_count":1,"area":null},{"id":"2111.03796","title":"Development of collective behavior in newborn artificial agents","created":"2021-11-06","cited_by_count":1,"area":null},{"id":"2112.01328","title":"Homotopy Based Reinforcement Learning with Maximum Entropy for Autonomous Air Combat","created":"2021-12-01","cited_by_count":1,"area":null},{"id":"2205.08856","title":"Bridging the gap between QP-based and MPC-based RL","created":"2022-05-18","cited_by_count":1,"area":null},{"id":"2206.06796","title":"Open-Ended Learning Strategies for Learning Complex Locomotion Skills","created":"2022-06-14","cited_by_count":1,"area":null},{"id":"2212.06001","title":"Reinforcement Learning and Tree Search Methods for the Unit Commitment Problem","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2402.06682","title":"Private Knowledge Sharing in Distributed Learning: A Survey","created":"2024-02-08","cited_by_count":1,"area":null},{"id":"2503.08061","title":"ForceGrip: Reference-Free Curriculum Learning for Realistic Grip Force Control in VR Hand Manipulation","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2503.17125","title":"LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning","created":"2025-03-21","cited_by_count":1,"area":null},{"id":"2504.02479","title":"Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets","created":"2025-04-03","cited_by_count":1,"area":null},{"id":"2103.12321","title":"Learning 6DoF Grasping Using Reward-Consistent Demonstration","created":"2021-03-23","cited_by_count":0,"area":null},{"id":"2104.04078","title":"Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks","created":"2021-04-06","cited_by_count":0,"area":null},{"id":"2108.02128","title":"Parallelized Reverse Curriculum Generation","created":"2021-08-04","cited_by_count":0,"area":null},{"id":"2109.05604","title":"Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies","created":"2021-09-12","cited_by_count":0,"area":null}],"next_cursor":"100"}