Bibliographic Details
| Title: |
Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank |
| Authors: |
Zhan, Wenhao, Fujimoto, Scott, Zhu, Zheqing, Lee, Jason D., Jiang, Daniel R., Efroni, Yonathan |
| Publication Year: |
2024 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Machine Learning |
| More Details: |
We study the problem of learning an approximate equilibrium in the offline multi-agent reinforcement learning (MARL) setting. We introduce a structural assumption -- the interaction rank -- and establish that functions with low interaction rank are significantly more robust to distribution shift compared to general ones. Leveraging this observation, we demonstrate that utilizing function classes with low interaction rank, when combined with regularization and no-regret learning, admits decentralized, computationally and statistically efficient learning in offline MARL. Our theoretical results are complemented by experiments that showcase the potential of critic architectures with low interaction rank in offline MARL, contrasting with commonly used single-agent value decomposition architectures. |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2410.01101 |
| Accession Number: |
edsarx.2410.01101 |
| Database: |
arXiv |
