All Learning Is Local: Multi-Agent Learning in Global Reward Games

Abstract

In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algo- rithms. We provide a simple and efficient algorithm that in part uses a linear system to model the world from a single agent’s limited per- spective, and takes advantage of Kalman filtering to allow an agent to construct a good training signal and learn an effective policy.

Cite

Text

Chang et al. "All Learning Is Local: Multi-Agent Learning in Global Reward Games." Neural Information Processing Systems, 2003.

Markdown

[Chang et al. "All Learning Is Local: Multi-Agent Learning in Global Reward Games." Neural Information Processing Systems, 2003.](https://mlanthology.org/neurips/2003/chang2003neurips-all/)

BibTeX

@inproceedings{chang2003neurips-all,
  title     = {{All Learning Is Local: Multi-Agent Learning in Global Reward Games}},
  author    = {Chang, Yu-han and Ho, Tracey and Kaelbling, Leslie P.},
  booktitle = {Neural Information Processing Systems},
  year      = {2003},
  pages     = {807-814},
  url       = {https://mlanthology.org/neurips/2003/chang2003neurips-all/}
}