UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914825320267776 |
|---|---|
| author | Zhang, Yu Yu, Rui Yao, Zhipeng Zhang, Wenyuan Wang, Jun Zhang, Liming |
| author_facet | Zhang, Yu Yu, Rui Yao, Zhipeng Zhang, Wenyuan Wang, Jun Zhang, Liming |
| contents | The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has achieved outstanding performance. However, we find that its principle can lead to overestimation phenomenon for the value function. In this paper, we first theoretically analyze overestimation phenomenon led by MSE and provide the theoretical upper bound of the overestimated error. Furthermore, to address it, we propose a novel Bellman underestimated operator to counteract overestimation phenomenon and then prove its contraction characteristics. At last, we propose the offline RL algorithm based on underestimated operator and diffusion policy model. Extensive experimental results on D4RL tasks show that our method can outperform state-of-the-art offline RL algorithms, which demonstrates that our theoretical analysis and underestimation way are effective for offline RL tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03324 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning Zhang, Yu Yu, Rui Yao, Zhipeng Zhang, Wenyuan Wang, Jun Zhang, Liming Machine Learning The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has achieved outstanding performance. However, we find that its principle can lead to overestimation phenomenon for the value function. In this paper, we first theoretically analyze overestimation phenomenon led by MSE and provide the theoretical upper bound of the overestimated error. Furthermore, to address it, we propose a novel Bellman underestimated operator to counteract overestimation phenomenon and then prove its contraction characteristics. At last, we propose the offline RL algorithm based on underestimated operator and diffusion policy model. Extensive experimental results on D4RL tasks show that our method can outperform state-of-the-art offline RL algorithms, which demonstrates that our theoretical analysis and underestimation way are effective for offline RL tasks. |
| title | UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.03324 |