{"list":"other","total":86,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"2108.10470","title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","created":"2021-08-24","cited_by_count":998},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1901.08652","title":"Learning agile and dynamic motor skills for legged robots","created":"2019-01-24","cited_by_count":504},{"id":"2201.08117","title":"Learning robust perceptive locomotion for quadrupedal robots in the wild","created":"2022-01-20","cited_by_count":382},{"id":"1804.10332","title":"Sim-to-Real: Learning Agile Locomotion For Quadruped Robots","created":"2018-04-27","cited_by_count":319},{"id":"2301.04195","title":"Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments","created":"2023-01-10","cited_by_count":295},{"id":"1812.03201","title":"Residual Reinforcement Learning for Robot Control","created":"2018-12-07","cited_by_count":274},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"2305.06456","title":"Perpetual Humanoid Control for Real-time Simulated Avatars","created":"2023-05-10","cited_by_count":218},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189},{"id":"2303.03381","title":"Real-World Humanoid Locomotion with Reinforcement Learning","created":"2023-03-06","cited_by_count":187},{"id":"2406.10454","title":"HumanPlus: Humanoid Shadowing and Imitation from Humans","created":"2024-06-15","cited_by_count":185},{"id":"2205.02824","title":"Rapid Locomotion via Reinforcement Learning","created":"2022-05-05","cited_by_count":168},{"id":"1812.06298","title":"Residual Policy Learning","created":"2018-12-15","cited_by_count":164},{"id":"1702.02453","title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","created":"2017-02-08","cited_by_count":141},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130},{"id":"2210.10044","title":"Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion","created":"2022-10-18","cited_by_count":121},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118},{"id":"2103.14295","title":"Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots","created":"2021-03-26","cited_by_count":116},{"id":"2409.14393","title":"MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting","created":"2024-09-22","cited_by_count":116},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104},{"id":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99},{"id":"2406.10759","title":"Humanoid Parkour Learning","created":"2024-06-15","cited_by_count":96},{"id":"2410.21229","title":"HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots","created":"2024-10-28","cited_by_count":91},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90},{"id":"2202.05481","title":"Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion","created":"2022-02-11","cited_by_count":88},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88},{"id":"1811.08027","title":"Neural Lander: Stable Drone Landing Control using Learned Dynamics","created":"2018-11-19","cited_by_count":85},{"id":"1906.01728","title":"BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators","created":"2019-06-04","cited_by_count":85},{"id":"2205.06908","title":"Neural-Fly Enables Rapid Learning for Agile Flight in Strong Winds","created":"2022-05-13","cited_by_count":85},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75},{"id":"2402.19469","title":"Humanoid Locomotion as Next Token Prediction","created":"2024-02-29","cited_by_count":69},{"id":"2301.10602","title":"DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning","created":"2023-01-25","cited_by_count":66},{"id":"2406.06005","title":"WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts","created":"2024-06-10","cited_by_count":61},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59},{"id":"1903.01390","title":"Sim-to-Real Transfer for Biped Locomotion","created":"2019-03-04","cited_by_count":56},{"id":"2408.14472","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","created":"2024-08-26","cited_by_count":56},{"id":"2205.15299","title":"Adapting Rapid Motor Adaptation for Bipedal Robots","created":"2022-05-30","cited_by_count":54},{"id":"2412.07773","title":"Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control","created":"2024-12-10","cited_by_count":51},{"id":"2411.14386","title":"Learning Humanoid Locomotion with Perceptive Internal Model","created":"2024-11-21","cited_by_count":50},{"id":"2104.07662","title":"Auto-Tuned Sim-to-Real Transfer","created":"2021-04-15","cited_by_count":49},{"id":"1909.12995","title":"Learning Fast Adaptation with Meta Strategy Optimization","created":"2019-09-28","cited_by_count":48},{"id":"2003.02471","title":"Data-efficient Domain Randomization with Bayesian Optimization","created":"2020-03-05","cited_by_count":47},{"id":"2406.14558","title":"CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics","created":"2024-06-20","cited_by_count":44},{"id":"1810.05751","title":"Policy Transfer with Strategy Optimization","created":"2018-10-12","cited_by_count":43},{"id":"2312.11460","title":"Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response","created":"2023-12-18","cited_by_count":39},{"id":"2203.00663","title":"Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects","created":"2022-03-01","cited_by_count":37},{"id":"1808.03246","title":"Augmenting Physical Simulators with Stochastic Neural Networks: Case Study of Planar Pushing and Bouncing","created":"2018-08-09","cited_by_count":36},{"id":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36},{"id":"2106.08050","title":"Residual Reinforcement Learning from Demonstrations","created":"2021-06-15","cited_by_count":31},{"id":"2402.18294","title":"Whole-body Humanoid Robot Locomotion with Human Reference","created":"2024-02-28","cited_by_count":29},{"id":"2407.00187","title":"SMPLOlympics: Sports Environments for Physically Simulated Humanoids","created":"2024-06-28","cited_by_count":29},{"id":"2008.07682","title":"Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulation","created":"2020-08-18","cited_by_count":28},{"id":"2405.10830","title":"CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion","created":"2024-05-17","cited_by_count":25},{"id":"2408.13740","title":"PIE: Parkour with Implicit-Explicit Learning Framework for Legged Robots","created":"2024-08-25","cited_by_count":25},{"id":"2407.21781","title":"Berkeley Humanoid: A Research Platform for Learning-based Control","created":"2024-07-31","cited_by_count":24},{"id":"2012.05457","title":"Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms using Learned Interactions","created":"2020-12-10","cited_by_count":20},{"id":"2407.16210","title":"Strategy and Skill Learning for Physics-based Table Tennis Animation","created":"2024-07-23","cited_by_count":20},{"id":"2008.01279","title":"Reinforced Grounded Action Transformation for Sim-to-Real Transfer","created":"2020-08-04","cited_by_count":18},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18},{"id":"2109.08815","title":"Probabilistic Inference of Simulation Parameters via Parallel Differentiable Simulation","created":"2021-09-18","cited_by_count":17},{"id":"2209.12878","title":"Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization","created":"2022-09-26","cited_by_count":17},{"id":"2310.09053","title":"DATT: Deep Adaptive Trajectory Tracking for Quadrotor Control","created":"2023-10-13","cited_by_count":16},{"id":"2409.15783","title":"AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility","created":"2024-09-24","cited_by_count":13},{"id":"2112.05068","title":"A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation","created":"2021-12-09","cited_by_count":11},{"id":"1710.04102","title":"Combining Learned and Analytical Models for Predicting Action Effects from Sensory Data","created":"2017-10-11","cited_by_count":10},{"id":"1809.10811","title":"Using Deep Reinforcement Learning to Learn High-Level Policies on the ATRIAS Biped","created":"2018-09-28","cited_by_count":10},{"id":"2207.13224","title":"PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representations","created":"2022-07-27","cited_by_count":10},{"id":"2311.01405","title":"Learning to See Physical Properties with Active Sensing Motor Policies","created":"2023-11-02","cited_by_count":10},{"id":"1901.08100","title":"Dynamic Locomotion For Passive-Ankle Biped Robots And Humanoids Using Whole-Body Locomotion Control","created":"2019-01-23","cited_by_count":8},{"id":"2409.09441","title":"PIP-Loco: A Proprioceptive Infinite Horizon Planning Framework for Quadrupedal Robot Locomotion","created":"2024-09-14","cited_by_count":7},{"id":"2409.10923","title":"Agile Continuous Jumping in Discontinuous Terrains","created":"2024-09-17","cited_by_count":7},{"id":"2203.03918","title":"Residual Robot Learning for Object-Centric Probabilistic Movement Primitives","created":"2022-03-08","cited_by_count":5},{"id":"2403.05868","title":"Toward Understanding Key Estimation in Learning Robust Humanoid Locomotion","created":"2024-03-09","cited_by_count":5},{"id":"2410.07575","title":"Self-Supervised Meta-Learning for All-Layer DNN-Based Adaptive Control with Stability Guarantees","created":"2024-10-10","cited_by_count":3},{"id":"2409.17992","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","created":"2024-09-26","cited_by_count":2},{"id":"2411.13079","title":"Neural Internal Model Control: Learning a Robust Control Policy via Predictive Error Feedback","created":"2024-11-20","cited_by_count":2}],"next_cursor":null}