Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2311.07822 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914959328280576 |
|---|---|
| author | Zhang, Pei Hua, Zhaobo Ding, Jinliang |
| author_facet | Zhang, Pei Hua, Zhaobo Ding, Jinliang |
| contents | The development of intelligent robots requires control policies that can handle dynamic environments and evolving tasks. Pre-training reinforcement learning has emerged as an effective approach to address these demands by enabling robots to acquire reusable motor skills. However, they often rely on large datasets or expert-designed goal spaces, limiting adaptability. Additionally, these methods need help to generate dynamic and diverse skills in high-dimensional state spaces, reducing their effectiveness for downstream tasks. In this paper, we propose CMS-PRL, a pre-training reinforcement learning method inspired by the Central Motor System (CMS). First, we introduce a fusion reward mechanism that combines the basic motor reward with mutual information reward, promoting the discovery of dynamic skills during pre-training without reliance on external data. Second, we design a skill encoding method inspired by the motor program of the basal ganglia, providing rich and continuous skill instructions during pre-training. Finally, we propose a skill activity function to regulate motor skill activity, enabling the generation of skills with different activity levels, thereby enhancing the robot's flexibility in downstream tasks. We evaluate the model on four types of robots in a challenging set of sparse-reward tasks. Experimental results demonstrate that CMS-PRL generates diverse, reusable motor skills to solve various downstream tasks and outperforms baseline methods, particularly in high-degree-of-freedom robots and complex tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_07822 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control Zhang, Pei Hua, Zhaobo Ding, Jinliang Robotics Artificial Intelligence The development of intelligent robots requires control policies that can handle dynamic environments and evolving tasks. Pre-training reinforcement learning has emerged as an effective approach to address these demands by enabling robots to acquire reusable motor skills. However, they often rely on large datasets or expert-designed goal spaces, limiting adaptability. Additionally, these methods need help to generate dynamic and diverse skills in high-dimensional state spaces, reducing their effectiveness for downstream tasks. In this paper, we propose CMS-PRL, a pre-training reinforcement learning method inspired by the Central Motor System (CMS). First, we introduce a fusion reward mechanism that combines the basic motor reward with mutual information reward, promoting the discovery of dynamic skills during pre-training without reliance on external data. Second, we design a skill encoding method inspired by the motor program of the basal ganglia, providing rich and continuous skill instructions during pre-training. Finally, we propose a skill activity function to regulate motor skill activity, enabling the generation of skills with different activity levels, thereby enhancing the robot's flexibility in downstream tasks. We evaluate the model on four types of robots in a challenging set of sparse-reward tasks. Experimental results demonstrate that CMS-PRL generates diverse, reusable motor skills to solve various downstream tasks and outperforms baseline methods, particularly in high-degree-of-freedom robots and complex tasks. |
| title | A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2311.07822 |