Optimistic critics can empower small actors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913990187155456 |
|---|---|
| author | Mastikhina, Olya Sreenivas, Dhruv Castro, Pablo Samuel |
| author_facet | Mastikhina, Olya Sreenivas, Dhruv Castro, Pablo Samuel |
| contents | Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, smaller actors result in performance degradation and overfit critics. Our analyses suggest poor data collection, due to value underestimation, as one of the main causes for this behavior, and further highlight the crucial role the critic can play in alleviating this pathology. We explore techniques to mitigate the observed value underestimation, which enables further research in asymmetric actor-critic methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01016 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimistic critics can empower small actors Mastikhina, Olya Sreenivas, Dhruv Castro, Pablo Samuel Machine Learning Actor-critic methods have been central to many of the recent advances in deep reinforcement learning. The most common approach is to use symmetric architectures, whereby both actor and critic have the same network topology and number of parameters. However, recent works have argued for the advantages of asymmetric setups, specifically with the use of smaller actors. We perform broad empirical investigations and analyses to better understand the implications of this and find that, in general, smaller actors result in performance degradation and overfit critics. Our analyses suggest poor data collection, due to value underestimation, as one of the main causes for this behavior, and further highlight the crucial role the critic can play in alleviating this pathology. We explore techniques to mitigate the observed value underestimation, which enables further research in asymmetric actor-critic methods. |
| title | Optimistic critics can empower small actors |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.01016 |