Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908610401927168 |
|---|---|
| author | Ma, Haozhe Luo, Zhengding Vo, Thanh Vinh Sima, Kuankuan Leong, Tze-Yun |
| author_facet | Ma, Haozhe Luo, Zhengding Vo, Thanh Vinh Sima, Kuankuan Leong, Tze-Yun |
| contents | Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task reinforcement learning framework that integrates a centralized reward agent (CRA) and multiple distributed policy agents. The CRA functions as a knowledge pool, aimed at distilling knowledge from various tasks and distributing it to individual policy agents to improve learning efficiency. Specifically, the shaped rewards serve as a straightforward metric for encoding knowledge. This framework not only enhances knowledge sharing across established tasks but also adapts to new tasks by transferring meaningful reward signals. We validate the proposed method on both discrete and continuous domains, including the representative Meta-World benchmark, demonstrating its robustness in multi-task sparse-reward settings and its effective transferability to unseen tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10858 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning Ma, Haozhe Luo, Zhengding Vo, Thanh Vinh Sima, Kuankuan Leong, Tze-Yun Machine Learning Artificial Intelligence Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task reinforcement learning framework that integrates a centralized reward agent (CRA) and multiple distributed policy agents. The CRA functions as a knowledge pool, aimed at distilling knowledge from various tasks and distributing it to individual policy agents to improve learning efficiency. Specifically, the shaped rewards serve as a straightforward metric for encoding knowledge. This framework not only enhances knowledge sharing across established tasks but also adapts to new tasks by transferring meaningful reward signals. We validate the proposed method on both discrete and continuous domains, including the representative Meta-World benchmark, demonstrating its robustness in multi-task sparse-reward settings and its effective transferability to unseen tasks. |
| title | Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.10858 |