Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912710083477504 |
|---|---|
| author | Ma, Guoqing Zhang, Yuhan Dai, Yuming Hao, Guangfu Chen, Yang Yu, Shan |
| author_facet | Ma, Guoqing Zhang, Yuhan Dai, Yuming Hao, Guangfu Chen, Yang Yu, Shan |
| contents | Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environmental stationarity, which poses a great challenge to learning efficiency since many environments are inherently non-stationary. This non-stationarity results in the requirement of millions of iterations, leading to low sample efficiency. To address this issue, we introduce the Clustering Orthogonal Weight Modified (COWM) layer, which can be integrated into the policy network of any RL algorithm and mitigate non-stationarity effectively. The COWM layer stabilizes the learning process by employing clustering techniques and a projection matrix. Our approach not only improves learning speed but also reduces gradient interference, thereby enhancing the overall learning efficiency. Empirically, the COWM outperforms state-of-the-art methods and achieves improvements of 9% and 12.6% in vision based and state-based DMControl benchmark. It also shows robustness and generality across various algorithms and tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11607 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning Ma, Guoqing Zhang, Yuhan Dai, Yuming Hao, Guangfu Chen, Yang Yu, Shan Machine Learning Artificial Intelligence Reinforcement learning (RL) has made significant advancements, achieving superhuman performance in various tasks. However, RL agents often operate under the assumption of environmental stationarity, which poses a great challenge to learning efficiency since many environments are inherently non-stationary. This non-stationarity results in the requirement of millions of iterations, leading to low sample efficiency. To address this issue, we introduce the Clustering Orthogonal Weight Modified (COWM) layer, which can be integrated into the policy network of any RL algorithm and mitigate non-stationarity effectively. The COWM layer stabilizes the learning process by employing clustering techniques and a projection matrix. Our approach not only improves learning speed but also reduces gradient interference, thereby enhancing the overall learning efficiency. Empirically, the COWM outperforms state-of-the-art methods and achieves improvements of 9% and 12.6% in vision based and state-based DMControl benchmark. It also shows robustness and generality across various algorithms and tasks. |
| title | Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.11607 |