Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.01409 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918163537461248 |
|---|---|
| author | Huang, Xi Zhou, Hongyi Li, Ge Tang, Yucheng Liao, Weiran Hein, Björn Asfour, Tamim Lioutikov, Rudolf |
| author_facet | Huang, Xi Zhou, Hongyi Li, Ge Tang, Yucheng Liao, Weiran Hein, Björn Asfour, Tamim Lioutikov, Rudolf |
| contents | We propose MoRe-ERL, a framework that combines Episodic Reinforcement Learning (ERL) and residual learning, which refines preplanned reference trajectories into safe, feasible, and efficient task-specific trajectories. This framework is general enough to incorporate into arbitrary ERL methods and motion generators seamlessly. MoRe-ERL identifies trajectory segments requiring modification while preserving critical task-related maneuvers. Then it generates smooth residual adjustments using B-Spline-based movement primitives to ensure adaptability to dynamic task contexts and smoothness in trajectory refinement. Experimental results demonstrate that residual learning significantly outperforms training from scratch using ERL methods, achieving superior sample efficiency and task performance. Hardware evaluations further validate the framework, showing that policies trained in simulation can be directly deployed in real-world systems, exhibiting a minimal sim-to-real gap. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement Learning Huang, Xi Zhou, Hongyi Li, Ge Tang, Yucheng Liao, Weiran Hein, Björn Asfour, Tamim Lioutikov, Rudolf Robotics Machine Learning We propose MoRe-ERL, a framework that combines Episodic Reinforcement Learning (ERL) and residual learning, which refines preplanned reference trajectories into safe, feasible, and efficient task-specific trajectories. This framework is general enough to incorporate into arbitrary ERL methods and motion generators seamlessly. MoRe-ERL identifies trajectory segments requiring modification while preserving critical task-related maneuvers. Then it generates smooth residual adjustments using B-Spline-based movement primitives to ensure adaptability to dynamic task contexts and smoothness in trajectory refinement. Experimental results demonstrate that residual learning significantly outperforms training from scratch using ERL methods, achieving superior sample efficiency and task performance. Hardware evaluations further validate the framework, showing that policies trained in simulation can be directly deployed in real-world systems, exhibiting a minimal sim-to-real gap. |
| title | MoRe-ERL: Learning Motion Residuals using Episodic Reinforcement Learning |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2508.01409 |