Subequivariant Reinforcement Learning Framework for Coordinated Motion Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917620290158592 |
|---|---|
| author | Wang, Haoyu Tan, Xiaoyu Qiu, Xihe Qu, Chao |
| author_facet | Wang, Haoyu Tan, Xiaoyu Qiu, Xihe Qu, Chao |
| contents | Effective coordination is crucial for motion control with reinforcement learning, especially as the complexity of agents and their motions increases. However, many existing methods struggle to account for the intricate dependencies between joints. We introduce CoordiGraph, a novel architecture that leverages subequivariant principles from physics to enhance coordination of motion control with reinforcement learning. This method embeds the principles of equivariance as inherent patterns in the learning process under gravity influence, which aids in modeling the nuanced relationships between joints vital for motion control. Through extensive experimentation with sophisticated agents in diverse environments, we highlight the merits of our approach. Compared to current leading methods, CoordiGraph notably enhances generalization and sample efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Subequivariant Reinforcement Learning Framework for Coordinated Motion Control Wang, Haoyu Tan, Xiaoyu Qiu, Xihe Qu, Chao Robotics Artificial Intelligence Effective coordination is crucial for motion control with reinforcement learning, especially as the complexity of agents and their motions increases. However, many existing methods struggle to account for the intricate dependencies between joints. We introduce CoordiGraph, a novel architecture that leverages subequivariant principles from physics to enhance coordination of motion control with reinforcement learning. This method embeds the principles of equivariance as inherent patterns in the learning process under gravity influence, which aids in modeling the nuanced relationships between joints vital for motion control. Through extensive experimentation with sophisticated agents in diverse environments, we highlight the merits of our approach. Compared to current leading methods, CoordiGraph notably enhances generalization and sample efficiency. |
| title | Subequivariant Reinforcement Learning Framework for Coordinated Motion Control |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2403.15100 |