{"total":89,"rows":[{"id":"2206.14176","title":"DayDreamer: World Models for Physical Robot Learning","created":"2022-06-28","cited_by_count":400,"area":"wm"},{"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":"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":"2401.16889","title":"Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control","created":"2024-01-30","cited_by_count":99,"area":"deeprl"},{"id":"2412.13196","title":"ExBody2: Advanced Expressive Humanoid Whole-Body Control","created":"2024-12-17","cited_by_count":88,"area":null},{"id":"2312.04393","title":"PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction","created":"2023-12-07","cited_by_count":76,"area":null},{"id":"2403.16967","title":"Visual Whole-Body Control for Legged Loco-Manipulation","created":"2024-03-25","cited_by_count":62,"area":null},{"id":"2412.07773","title":"Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control","created":"2024-12-10","cited_by_count":51,"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":"2404.19264","title":"DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasets","created":"2024-04-30","cited_by_count":49,"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":"2206.11693","title":"Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations","created":"2022-06-23","cited_by_count":45,"area":null},{"id":"2308.12270","title":"Language Reward Modulation for Pretraining Reinforcement Learning","created":"2023-08-23","cited_by_count":43,"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":"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":"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":"2206.14349","title":"Fleet-DAgger: Interactive Robot Fleet Learning with Scalable Human Supervision","created":"2022-06-29","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":"2402.18294","title":"Whole-body Humanoid Robot Locomotion with Human Reference","created":"2024-02-28","cited_by_count":29,"area":"offlinerl"},{"id":"2305.17842","title":"RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion","created":"2023-05-29","cited_by_count":26,"area":null},{"id":"2210.04435","title":"Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning","created":"2022-10-10","cited_by_count":23,"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":"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":"2501.05204","title":"Design and Control of a Bipedal Robotic Character","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2510.11072","title":"PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System","created":"2025-10-13","cited_by_count":18,"area":null},{"id":"2409.15780","title":"A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards","created":"2024-09-24","cited_by_count":12,"area":"deeprl"},{"id":"2503.01837","title":"Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning","created":"2025-03-03","cited_by_count":11,"area":"wm"},{"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":"2410.13817","title":"Guided Reinforcement Learning for Robust Multi-Contact Loco-Manipulation","created":"2024-10-17","cited_by_count":10,"area":"deeprl"},{"id":"2506.08840","title":"MoRE: Mixture of Residual Experts for Humanoid Lifelike Gaits Learning on Complex Terrains","created":"2025-06-10","cited_by_count":10,"area":"deeprl"},{"id":"2506.09366","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","created":"2025-06-11","cited_by_count":9,"area":"deeprl"},{"id":"2303.09597","title":"Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2304.10888","title":"Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild","created":"2023-04-21","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":"2410.13586","title":"Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control","created":"2024-10-17","cited_by_count":7,"area":"diffusion"},{"id":"2502.01465","title":"Embrace Collisions: Humanoid Shadowing for Deployable Contact-Agnostics Motions","created":"2025-02-03","cited_by_count":7,"area":"deeprl"},{"id":"2505.20619","title":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","created":"2025-05-27","cited_by_count":6,"area":"deeprl"},{"id":"2505.16084","title":"Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility","created":"2025-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2509.01765","title":"Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control","created":"2025-09-01","cited_by_count":5,"area":"deeprl"},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","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":"2503.21401","title":"AcL: Action Learner for Fault-Tolerant Quadruped Locomotion Control","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2507.05674","title":"Integrating Diffusion-based Multi-task Learning with Online Reinforcement Learning for Robust Quadruped Robot Control","created":"2025-07-08","cited_by_count":3,"area":"diffusion"},{"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":"2509.16061","title":"Latent Conditioned Loco-Manipulation Using Motion Priors","created":"2025-09-19","cited_by_count":3,"area":"deeprl"},{"id":"2602.08370","title":"Learning Human-Like Badminton Skills for Humanoid Robots","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2603.07516","title":"InterReal: A Unified Physics-Based Imitation Framework for Learning Human-Object Interaction Skills","created":"2026-03-08","cited_by_count":3,"area":null},{"id":"2312.17606","title":"Adaptive Control Strategy for Quadruped Robots in Actuator Degradation Scenarios","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2403.01962","title":"An Efficient Model-Based Approach on Learning Agile Motor Skills without Reinforcement","created":"2024-03-04","cited_by_count":2,"area":"wm"},{"id":"2409.17992","title":"LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots","created":"2024-09-26","cited_by_count":2,"area":"deeprl"},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2506.12529","title":"Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning","created":"2025-06-14","cited_by_count":2,"area":"alignment"},{"id":"2507.05906","title":"Feature-Based vs. GAN-Based Learning from Demonstrations: When and Why","created":"2025-07-08","cited_by_count":2,"area":"offlinerl"},{"id":"2510.11542","title":"NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning","created":"2025-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2306.08224","title":"Expanding Versatility of Agile Locomotion through Policy Transitions Using Latent State Representation","created":"2023-06-14","cited_by_count":1,"area":null},{"id":"2310.10610","title":"Quantifying Assistive Robustness Via the Natural-Adversarial Frontier","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2407.17502","title":"MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation","created":"2024-07-05","cited_by_count":1,"area":"deeprl"},{"id":"2411.01349","title":"The Role of Domain Randomization in Training Diffusion Policies for Whole-Body Humanoid Control","created":"2024-11-02","cited_by_count":1,"area":"diffusion"},{"id":"2504.19480","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2507.02256","title":"Uncertainty-aware Reward Design Process","created":"2025-07-03","cited_by_count":1,"area":"lr"},{"id":"2509.05581","title":"Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids","created":"2025-09-06","cited_by_count":1,"area":"deeprl"},{"id":"2601.15995","title":"PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2605.08804","title":"Constraint-Aware Diffusion Priors for High-Fidelity and Versatile Quadruped Locomotion","created":"2026-05-09","cited_by_count":1,"area":"diffusion"},{"id":"2606.26392","title":"MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basins","created":"2026-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2607.03454","title":"ADP: Adversarial Dynamics Priors for Physically Grounded Humanoid Locomotion","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.13579","title":"Agile perceptive multi-skill locomotion for quadrupedal robots in the wild","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2311.06015","title":"Unlock Reliable Skill Inference for Quadruped Adaptive Behavior by Skill Graph","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2406.17795","title":"RACon: Retrieval-Augmented Simulated Character Locomotion Control","created":"2024-06-11","cited_by_count":0,"area":null},{"id":"2408.03018","title":"Integrating Controllable Motion Skills from Demonstrations","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2503.04462","title":"PALo: Learning Posture-Aware Locomotion for Quadruped Robots","created":"2025-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2504.05629","title":"PTRL: Prior Transfer Deep Reinforcement Learning for Legged Robots Locomotion","created":"2025-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2504.10390","title":"Teacher Motion Priors: Enhancing Robot Locomotion over Challenging Terrain","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2509.24539","title":"Unlocking the Potential of Soft Actor-Critic for Imitation Learning","created":"2025-09-29","cited_by_count":0,"area":"offlinerl"},{"id":"2510.09543","title":"Guiding Energy-Efficient Locomotion through Impact Mitigation Rewards","created":"2025-10-10","cited_by_count":0,"area":"deeprl"},{"id":"2511.03167","title":"Learning Natural and Robust Hexapod Locomotion over Complex Terrains via Motion Priors based on Deep Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2603.21853","title":"Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.24047","title":"PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning","created":"2026-03-25","cited_by_count":0,"area":"deeprl"},{"id":"2604.16440","title":"LatentMimic: Terrain-Adaptive Locomotion via Latent Space Imitation","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.19102","title":"Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2606.07083","title":"Predictive Style Matching: Natural and Robust Humanoid Locomotion","created":"2026-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2606.15896","title":"LoComposition: Terrain-Adaptive Energy-Efficient Quadruped Locomotion without Gait Priors","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2608.03227","title":"PFM-HR: Pose Flow Matching for Humanoid Robots","created":"2026-08-04","cited_by_count":0,"area":"diffusion"},{"id":"2609.20566","title":"OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.10601","title":"Teaching a Robot Dog New Tricks: Diverse Quadruped Skills via Combined Reinforcement and Imitation Learning with Adversarial Task Selection","created":"2026-10-06","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}