ICML 2019oral200 citations
Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning
Jakob Foerster, Francis Song, Edward Hughes, Neil Burch, Iain Dunning, Shimon Whiteson, Matthew Botvinick, Michael Bowling
Abstract
When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act informatively and thereby communicate efficiently with others. Although learning algorithms have recently achieved superhuman performance in a number of two-player, zero-sum games, scalable multi-agent reinforcement learning algorithms that can discover effective strategies and conventions in complex, partially observable settings have proven elusive. We present the
BibTeX
@InProceedings{pmlr-v97-foerster19a,
title = {{B}ayesian Action Decoder for Deep Multi-Agent Reinforcement Learning},
author = {Foerster, Jakob and Song, Francis and Hughes, Edward and Burch, Neil and Dunning, Iain and Whiteson, Shimon and Botvinick, Matthew and Bowling, Michael},
booktitle = {Proceedings of the 36th International Conference on Machine Learning},
pages = {1942--1951},
year = {2019},
editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
volume = {97},
series = {Proceedings of Machine Learning Research},
month = {09--15 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v97/foerster19a/foerster19a.pdf},
url = {https://proceedings.mlr.press/v97/foerster19a.html},
abstract = {When observing the actions of others, humans make inferences about why they acted as they did, and what this implies about the world; humans also use the fact that their actions will be interpreted in this manner, allowing them to act informatively and thereby communicate efficiently with others. Although learning algorithms have recently achieved superhuman performance in a number of two-player, zero-sum games, scalable multi-agent reinforcement learning algorithms that can discover effective strategies and conventions in complex, partially observable settings have proven elusive. We present the