{"total":15,"rows":[{"id":"2505.23708","title":"AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning","created":"2025-05-29","cited_by_count":9,"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":"2603.18408","title":"Efficient and Versatile Quadrupedal Skating: Optimal Co-design via Reinforcement Learning and Bayesian Optimization","created":"2026-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2602.12724","title":"TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions","created":"2026-02-13","cited_by_count":1,"area":"deeprl"},{"id":"2603.17092","title":"SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for Locomotion","created":"2026-03-17","cited_by_count":1,"area":"deeprl"},{"id":"2502.00835","title":"CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation","created":"2025-02-02","cited_by_count":0,"area":"deeprl"},{"id":"2504.14989","title":"Dynamic Legged Ball Manipulation on Rugged Terrains with Hierarchical Reinforcement Learning","created":"2025-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2505.12222","title":"Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Study","created":"2025-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2506.05115","title":"Whole-Body Constrained Learning for Legged Locomotion via Hierarchical Optimization","created":"2025-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2509.13737","title":"Dynamic Adaptive Legged Locomotion Policy via Decoupling Reaction Force Control and Gait Control","created":"2025-09-17","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":"2607.08925","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","created":"2026-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.24036","title":"WARL: Wrench-Augmented Reinforcement Learning for Task-Agnostic Learning in Legged Robots","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.00880","title":"Bicycle Acrobatics with Reinforcement Learning","created":"2026-08-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02198","title":"FERPO: Forward Entropy-Regularized Policy Optimization","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}