Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach
Roel Dobbe, David Fridovich-Keil, Claire Tomlin
Abstract
Learning cooperative policies for multi-agent systems is often challenged by partial observability and a lack of coordination. In some settings, the structure of a problem allows a distributed solution with limited communication. Here, we consider a scenario where no communication is available, and instead we learn local policies for all agents that collectively mimic the solution to a centralized multi-agent static optimization problem. Our main contribution is an information theoretic framework based on rate distortion theory which facilitates analysis of how well the resulting fully decentralized policies are able to reconstruct the optimal solution. Moreover, this framework provides a natural extension that addresses which nodes an agent should communicate with to improve the performance of its individual policy.
BibTeX
@inproceedings{NIPS2017_8bb88f80,
author = {Dobbe, Roel and Fridovich-Keil, David and Tomlin, Claire},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Fully Decentralized Policies for Multi-Agent Systems: An Information Theoretic Approach},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/8bb88f80d334b1869781beb89f7b73be-Paper.pdf},
volume = {30},
year = {2017}
}