{"total":151,"rows":[{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386,"area":"wm"},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327,"area":"offlinerl"},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2309.14341","title":"Extreme Parkour with Legged Robots","created":"2023-09-25","cited_by_count":164,"area":null},{"id":"2309.05665","title":"Robot Parkour Learning","created":"2023-09-11","cited_by_count":149,"area":null},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145,"area":"offlinerl"},{"id":"2402.16796","title":"Expressive Whole-Body Control for Humanoid Robots","created":"2024-02-26","cited_by_count":139,"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":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2309.06440","title":"LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning","created":"2023-09-12","cited_by_count":79,"area":null},{"id":"2409.10161","title":"SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting","created":"2024-09-16","cited_by_count":69,"area":null},{"id":"2505.03729","title":"Visual Imitation Enables Contextual Humanoid Control","created":"2025-05-06","cited_by_count":68,"area":null},{"id":"2305.16309","title":"Imitating Task and Motion Planning with Visuomotor Transformers","created":"2023-05-25","cited_by_count":66,"area":"offlinerl"},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62,"area":null},{"id":"2307.08927","title":"Multi-Stage Cable Routing through Hierarchical Imitation Learning","created":"2023-07-18","cited_by_count":60,"area":"offlinerl"},{"id":"2309.15462","title":"DTC: Deep Tracking Control","created":"2023-09-27","cited_by_count":56,"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":"2405.01534","title":"Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks","created":"2024-05-02","cited_by_count":52,"area":null},{"id":"2505.03738","title":"AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control","created":"2025-05-06","cited_by_count":51,"area":null},{"id":"2405.01792","title":"Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots","created":"2024-05-03","cited_by_count":48,"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":"2304.01201","title":"Neural Volumetric Memory for Visual Locomotion Control","created":"2023-04-03","cited_by_count":44,"area":null},{"id":"2305.14654","title":"Barkour: Benchmarking Animal-level Agility with Quadruped Robots","created":"2023-05-24","cited_by_count":41,"area":null},{"id":"2304.01159","title":"DribbleBot: Dynamic Legged Manipulation in the Wild","created":"2023-04-03","cited_by_count":40,"area":null},{"id":"2303.11330","title":"Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion","created":"2023-03-20","cited_by_count":39,"area":null},{"id":"2312.02975","title":"Dexterous Functional Grasping","created":"2023-12-05","cited_by_count":39,"area":null},{"id":"2312.11460","title":"Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response","created":"2023-12-18","cited_by_count":39,"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":"2302.09450","title":"Robust and Versatile Bipedal Jumping Control through Reinforcement Learning","created":"2023-02-19","cited_by_count":36,"area":null},{"id":"2304.09834","title":"Learning and Adapting Agile Locomotion Skills by Transferring Experience","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2403.14864","title":"Learning Quadruped Locomotion Using Differentiable Simulation","created":"2024-03-21","cited_by_count":32,"area":null},{"id":"2403.12203","title":"Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight","created":"2024-03-18","cited_by_count":31,"area":"deeprl"},{"id":"2405.07991","title":"SPIN: Simultaneous Perception, Interaction and Navigation","created":"2024-05-13","cited_by_count":29,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2402.10837","title":"Pedipulate: Enabling Manipulation Skills using a Quadruped Robot's Leg","created":"2024-02-16","cited_by_count":27,"area":null},{"id":"2405.10830","title":"CTS: Concurrent Teacher-Student Reinforcement Learning for Legged Locomotion","created":"2024-05-17","cited_by_count":25,"area":"deeprl"},{"id":"2510.20808","title":"The Reality Gap in Robotics: Challenges, Solutions, and Best Practices","created":"2025-10-23","cited_by_count":24,"area":null},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22,"area":null},{"id":"2407.08725","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","created":"2024-07-11","cited_by_count":21,"area":"wm"},{"id":"2407.20230","title":"SAPG: Split and Aggregate Policy Gradients","created":"2024-07-29","cited_by_count":21,"area":"deeprl"},{"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":"2403.20328","title":"Learning Visual Quadrupedal Loco-Manipulation from Demonstrations","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2310.01408","title":"Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior","created":"2023-10-02","cited_by_count":19,"area":null},{"id":"2409.05864","title":"Neural MP: A Generalist Neural Motion Planner","created":"2024-09-09","cited_by_count":19,"area":null},{"id":"2505.22974","title":"Learning coordinated badminton skills for legged manipulators","created":"2025-05-29","cited_by_count":19,"area":"deeprl"},{"id":"2602.15827","title":"Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching","created":"2026-02-17","cited_by_count":19,"area":null},{"id":"2401.16337","title":"Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design","created":"2024-01-29","cited_by_count":18,"area":"deeprl"},{"id":"2407.11562","title":"RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewards","created":"2024-07-16","cited_by_count":18,"area":null},{"id":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18,"area":"wm"},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"area":"deeprl"},{"id":"2411.01775","title":"Eurekaverse: Environment Curriculum Generation via Large Language Models","created":"2024-11-04","cited_by_count":16,"area":null},{"id":"2505.00690","title":"Towards Autonomous Micromobility through Scalable Urban Simulation","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2309.09865","title":"Contrastive Learning for Enhancing Robust Scene Transfer in Vision-based Agile Flight","created":"2023-09-18","cited_by_count":15,"area":null},{"id":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15,"area":"lr"},{"id":"2309.14246","title":"Learning Risk-Aware Quadrupedal Locomotion using Distributional Reinforcement Learning","created":"2023-09-25","cited_by_count":14,"area":null},{"id":"2409.13678","title":"SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience","created":"2024-09-20","cited_by_count":14,"area":"deeprl"},{"id":"2309.03315","title":"Robotic Table Tennis: A Case Study into a High Speed Learning System","created":"2023-09-06","cited_by_count":13,"area":null},{"id":"2409.15755","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","created":"2024-09-24","cited_by_count":13,"area":"deeprl"},{"id":"2506.03404","title":"The Impact of On-Policy Parallelized Data Collection on Deep Reinforcement Learning Networks","created":"2025-06-03","cited_by_count":13,"area":"deeprl"},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2305.18464","title":"Bridging the Sim-to-Real Gap from the Information Bottleneck Perspective","created":"2023-05-29","cited_by_count":10,"area":null},{"id":"2311.01405","title":"Learning to See Physical Properties with Active Sensing Motor Policies","created":"2023-11-02","cited_by_count":10,"area":null},{"id":"2311.03357","title":"Exploitation-Guided Exploration for Semantic Embodied Navigation","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2403.03848","title":"Dexterous Legged Locomotion in Confined 3D Spaces with Reinforcement Learning","created":"2024-03-06","cited_by_count":9,"area":"deeprl"},{"id":"2405.14073","title":"PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning","created":"2024-05-23","cited_by_count":9,"area":"deeprl"},{"id":"2409.20445","title":"Robot Navigation Using Physically Grounded Vision-Language Models in Outdoor Environments","created":"2024-09-30","cited_by_count":9,"area":"mllm"},{"id":"2412.09989","title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2506.19212","title":"Scaffolding Dexterous Manipulation with Vision-Language Models","created":"2025-06-24","cited_by_count":9,"area":"mllm"},{"id":"2304.08663","title":"Continuous Versatile Jumping Using Learned Action Residuals","created":"2023-04-17","cited_by_count":8,"area":null},{"id":"2311.01059","title":"Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deployment","created":"2023-11-02","cited_by_count":8,"area":null},{"id":"2407.04224","title":"PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots","created":"2024-07-05","cited_by_count":8,"area":"deeprl"},{"id":"2410.00231","title":"Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2503.08375","title":"Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion","created":"2025-03-11","cited_by_count":8,"area":"deeprl"},{"id":"2303.07026","title":"Visual-Policy Learning through Multi-Camera View to Single-Camera View Knowledge Distillation for Robot Manipulation Tasks","created":"2023-03-13","cited_by_count":7,"area":"distill"},{"id":"2409.07409","title":"Robust Robot Walker: Learning Agile Locomotion over Tiny Traps","created":"2024-09-11","cited_by_count":7,"area":null},{"id":"2502.01465","title":"Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions","created":"2025-02-03","cited_by_count":7,"area":"deeprl"},{"id":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2409.19709","title":"DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning","created":"2024-09-29","cited_by_count":6,"area":"deeprl"},{"id":"2410.10766","title":"Adaptive Diffusion Terrain Generator for Autonomous Uneven Terrain Navigation","created":"2024-10-14","cited_by_count":6,"area":"diffusion"},{"id":"2505.06584","title":"JAEGER: Dual-Level Humanoid Whole-Body Controller","created":"2025-05-10","cited_by_count":6,"area":null},{"id":"2601.07701","title":"Deep Whole-body Parkour","created":"2026-01-12","cited_by_count":6,"area":null},{"id":"2307.15320","title":"Robust Visual Sim-to-Real Transfer for Robotic Manipulation","created":"2023-07-28","cited_by_count":5,"area":null},{"id":"2405.08726","title":"I-CTRL: Imitation to Control Humanoid Robots Through Constrained Reinforcement Learning","created":"2024-05-14","cited_by_count":5,"area":"deeprl"},{"id":"2509.16434","title":"End-to-end RL Improves Dexterous Grasping Policies","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2307.05891","title":"PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks","created":"2023-07-12","cited_by_count":4,"area":null},{"id":"2403.01928","title":"ZSL-RPPO: Zero-Shot Learning for Quadrupedal Locomotion in Challenging Terrains using Recurrent Proximal Policy Optimization","created":"2024-03-04","cited_by_count":4,"area":"deeprl"},{"id":"2406.16578","title":"QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2406.17279","title":"Learning Decentralized Multi-Biped Control for Payload Transport","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2407.06584","title":"HiLMa-Res: A General Hierarchical Framework via Residual RL for Combining Quadrupedal Locomotion and Manipulation","created":"2024-07-09","cited_by_count":4,"area":"deeprl"},{"id":"2501.09905","title":"SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor Learning","created":"2025-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2509.20036","title":"MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping","created":"2025-09-24","cited_by_count":4,"area":"deeprl"},{"id":"2304.12289","title":"Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics","created":"2023-04-24","cited_by_count":3,"area":null},{"id":"2306.01906","title":"Synaptic motor adaptation: A three-factor learning rule for adaptive robotic control in spiking neural networks","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2309.04370","title":"Seeing-Eye Quadruped Navigation with Force Responsive Locomotion Control","created":"2023-09-08","cited_by_count":3,"area":null},{"id":"2401.15484","title":"R$\\times$R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training","created":"2024-01-27","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}