{"total":147,"rows":[{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130,"area":"deeprl"},{"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":"2409.06366","title":"One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion","created":"2024-09-10","cited_by_count":43,"area":"deeprl"},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2410.11825","title":"Learning Smooth Humanoid Locomotion through Lipschitz-Constrained Policies","created":"2024-10-15","cited_by_count":30,"area":"deeprl"},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2406.06092","title":"Sim-To-Real Transfer for Visual Reinforcement Learning of Deformable Object Manipulation for Robot-Assisted Surgery","created":"2024-06-10","cited_by_count":26,"area":"deeprl"},{"id":"2402.15399","title":"Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation","created":"2024-02-23","cited_by_count":25,"area":"deeprl"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2411.01200","title":"GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation","created":"2024-11-02","cited_by_count":22,"area":"deeprl"},{"id":"2502.01536","title":"VR-Robo: A Real-to-Sim-to-Real Framework for Visual Robot Navigation and Locomotion","created":"2025-02-03","cited_by_count":22,"area":"deeprl"},{"id":"2409.20521","title":"Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning","created":"2024-09-30","cited_by_count":16,"area":"deeprl"},{"id":"2512.01996","title":"Learning Sim-to-Real Humanoid Locomotion in 15 Minutes","created":"2025-12-01","cited_by_count":16,"area":"deeprl"},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"area":"deeprl"},{"id":"2405.17416","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","created":"2024-05-27","cited_by_count":14,"area":"deeprl"},{"id":"2510.17792","title":"SoftMimic: Learning Compliant Whole-body Control from Examples","created":"2025-10-20","cited_by_count":14,"area":"deeprl"},{"id":"2405.15384","title":"Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate","created":"2024-05-24","cited_by_count":10,"area":"deeprl"},{"id":"2405.11982","title":"Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space","created":"2024-05-20","cited_by_count":9,"area":"deeprl"},{"id":"2512.02011","title":"Learning Dexterous Manipulation Skills from Imperfect Simulations","created":"2025-12-01","cited_by_count":9,"area":"deeprl"},{"id":"2403.12193","title":"Continual Domain Randomization","created":"2024-03-18","cited_by_count":8,"area":"deeprl"},{"id":"2407.04224","title":"PA-LOCO: Learning Perturbation-Adaptive Locomotion for Quadruped Robots","created":"2024-07-05","cited_by_count":8,"area":"deeprl"},{"id":"2411.03810","title":"Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data","created":"2024-11-06","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2604.02523","title":"Tune to Learn: How Controller Gains Shape Robot Policy Learning","created":"2026-04-02","cited_by_count":8,"area":"deeprl"},{"id":"2410.16632","title":"Benchmarking Smoothness and Reducing High-Frequency Oscillations in Continuous Control Policies","created":"2024-10-22","cited_by_count":7,"area":"deeprl"},{"id":"2508.12252","title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids","created":"2025-08-17","cited_by_count":7,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2403.02018","title":"Cross Domain Policy Transfer with Effect Cycle-Consistency","created":"2024-03-04","cited_by_count":5,"area":"deeprl"},{"id":"2404.09521","title":"Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning","created":"2024-04-15","cited_by_count":5,"area":"deeprl"},{"id":"2502.01546","title":"Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning","created":"2025-02-03","cited_by_count":5,"area":"deeprl"},{"id":"2503.24371","title":"Policy Gradient for LQR with Domain Randomization","created":"2025-03-31","cited_by_count":5,"area":"deeprl"},{"id":"2605.06500","title":"Operator-Guided Invariance Learning for Continuous Reinforcement Learning","created":"2026-05-07","cited_by_count":5,"area":"deeprl"},{"id":"2403.08152","title":"Multi-Fidelity Reinforcement Learning for Time-Optimal Quadrotor Re-planning","created":"2024-03-13","cited_by_count":4,"area":"deeprl"},{"id":"2406.00887","title":"Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations","created":"2024-06-02","cited_by_count":4,"area":"deeprl"},{"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":"2502.01800","title":"Flow-based Domain Randomization for Learning and Sequencing Robotic Skills","created":"2025-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2502.02869","title":"Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds","created":"2025-02-05","cited_by_count":4,"area":"deeprl"},{"id":"2502.19308","title":"WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies","created":"2025-02-26","cited_by_count":4,"area":"deeprl"},{"id":"2511.04249","title":"Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies","created":"2025-11-06","cited_by_count":4,"area":"deeprl"},{"id":"2603.20147","title":"AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learning","created":"2026-03-20","cited_by_count":4,"area":"deeprl"},{"id":"2406.19825","title":"Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems","created":"2024-06-28","cited_by_count":3,"area":"deeprl"},{"id":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2501.16590","title":"Benchmarking Model Predictive Control and Reinforcement Learning Based Control for Legged Robot Locomotion in MuJoCo Simulation","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2505.07321","title":"Drive Fast, Learn Faster: On-Board RL for High Performance Autonomous Racing","created":"2025-05-12","cited_by_count":3,"area":"deeprl"},{"id":"2505.12462","title":"Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis","created":"2025-05-18","cited_by_count":3,"area":"deeprl"},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2506.00472","title":"Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2406.06460","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","created":"2024-06-10","cited_by_count":2,"area":"deeprl"},{"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":"2503.10949","title":"Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics","created":"2025-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2509.14848","title":"Multi-Fidelity Hybrid Reinforcement Learning via Information Gain Maximization","created":"2025-09-18","cited_by_count":2,"area":"deeprl"},{"id":"2602.00678","title":"Toward Reliable Sim-to-Real Predictability for MoE-based Robust Quadrupedal Locomotion","created":"2026-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2602.19699","title":"CACTO-BIC: Scalable Actor-Critic Learning via Biased Sampling and GPU-Accelerated Trajectory Optimization","created":"2026-02-23","cited_by_count":2,"area":"deeprl"},{"id":"2604.10974","title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","created":"2026-04-13","cited_by_count":2,"area":"deeprl"},{"id":"2607.15003","title":"SMC-ES: Automated synthesis of formally verified control policies","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2403.14860","title":"Robust Model Based Reinforcement Learning Using $\\mathcal{L}_1$ Adaptive Control","created":"2024-03-21","cited_by_count":1,"area":"deeprl"},{"id":"2404.08246","title":"Agile and versatile bipedal robot tracking control through reinforcement learning","created":"2024-04-12","cited_by_count":1,"area":"deeprl"},{"id":"2405.10576","title":"An Efficient Learning Control Framework With Sim-to-Real for String-Type Artificial Muscle-Driven Robotic Systems","created":"2024-05-17","cited_by_count":1,"area":"deeprl"},{"id":"2406.17066","title":"Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems","created":"2024-06-24","cited_by_count":1,"area":"deeprl"},{"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":"2407.19860","title":"Anomalous State Sequence Modeling to Enhance Safety in Reinforcement Learning","created":"2024-07-29","cited_by_count":1,"area":"deeprl"},{"id":"2410.04719","title":"Domains as Objectives: Domain-Uncertainty-Aware Policy Optimization through Explicit Multi-Domain Convex Coverage Set Learning","created":"2024-10-07","cited_by_count":1,"area":"deeprl"},{"id":"2410.06570","title":"Disturbance Observer-based Control Barrier Functions with Residual Model Learning for Safe Reinforcement Learning","created":"2024-10-09","cited_by_count":1,"area":"deeprl"},{"id":"2411.04915","title":"Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping","created":"2024-11-07","cited_by_count":1,"area":"deeprl"},{"id":"2503.00499","title":"Shaping Laser Pulses with Reinforcement Learning","created":"2025-03-01","cited_by_count":1,"area":"deeprl"},{"id":"2504.15414","title":"Post-Convergence Sim-to-Real Policy Transfer: A Principled Alternative to Cherry-Picking","created":"2025-04-21","cited_by_count":1,"area":"deeprl"},{"id":"2505.06357","title":"DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition","created":"2025-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2505.18418","title":"McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal Locomotion","created":"2025-05-23","cited_by_count":1,"area":"deeprl"},{"id":"2506.12735","title":"Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling","created":"2025-06-15","cited_by_count":1,"area":"deeprl"},{"id":"2507.03068","title":"Mitigating Goal Misgeneralization via Minimax Regret","created":"2025-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2510.25063","title":"Control Synthesis with Reinforcement Learning: A Modeling Perspective","created":"2025-10-29","cited_by_count":1,"area":"deeprl"},{"id":"2601.14957","title":"Improving Regret Approximation for Unsupervised Dynamic Environment Generation","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2603.12543","title":"CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2603.15084","title":"HALO:Closing Sim-to-Real Gap for Heavy-loaded Humanoid Agile Motion Skills via Differentiable Simulation","created":"2026-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2604.02348","title":"Contextual Intelligence The Next Leap for Reinforcement Learning","created":"2026-02-17","cited_by_count":1,"area":"deeprl"},{"id":"2605.05110","title":"LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts","created":"2026-05-06","cited_by_count":1,"area":"deeprl"},{"id":"2606.11092","title":"RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning","created":"2026-06-09","cited_by_count":1,"area":"deeprl"},{"id":"2606.18594","title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","created":"2026-06-17","cited_by_count":1,"area":"deeprl"},{"id":"2606.31043","title":"Warp RL: Reshaping Base Policy Distributions for Dynamics Adaptation","created":"2026-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2608.03562","title":"Robust General Utility for Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"deeprl"},{"id":"2608.26469","title":"Active Curriculum Refinement for Reinforcement Learning","created":"2026-08-26","cited_by_count":1,"area":"deeprl"},{"id":"2609.13516","title":"Constraint-Grounded Reinforcement Learning for Variable Impedance Control in Contact-Rich Robotic Insertion","created":"2026-09-11","cited_by_count":1,"area":"deeprl"},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2404.08089","title":"Efficient Duple Perturbation Robustness in Low-rank MDPs","created":"2024-04-11","cited_by_count":0,"area":"deeprl"},{"id":"2404.13879","title":"Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty","created":"2024-04-22","cited_by_count":0,"area":"deeprl"},{"id":"2405.02598","title":"UDUC: An Uncertainty-driven Approach for Learning-based Robust Control","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2406.08069","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","created":"2024-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2407.00889","title":"Non-Prehensile Aerial Manipulation using Model-Based Deep Reinforcement Learning","created":"2024-07-01","cited_by_count":0,"area":"deeprl"},{"id":"2409.18289","title":"Criticality and Safety Margins for Reinforcement Learning","created":"2024-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2410.12250","title":"Dual Action Policy for Robust Sim-to-Real Reinforcement Learning","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2410.19852","title":"Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts","created":"2024-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2502.07133","title":"Cross-platform Learning-based Fault Tolerant Surfacing Controller for Underwater Robots","created":"2025-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2502.15649","title":"A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications","created":"2025-02-21","cited_by_count":0,"area":"deeprl"},{"id":"2503.11059","title":"Training Directional Locomotion for Quadrupedal Low-Cost Robotic Systems via Deep Reinforcement Learning","created":"2025-03-14","cited_by_count":0,"area":"deeprl"},{"id":"2503.11065","title":"Low-cost Real-world Implementation of the Swing-up Pendulum for Deep Reinforcement Learning Experiments","created":"2025-03-14","cited_by_count":0,"area":"deeprl"},{"id":"2503.14554","title":"Synchronous vs Asynchronous Reinforcement Learning in a Real World Robot","created":"2025-03-17","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}