Asynchronous Coagent Networks
Abstract
Coagent policy gradient algorithms (CPGAs) are reinforcement learning algorithms for training a class of stochastic neural networks called coagent networks. In this work, we prove that CPGAs converge to locally optimal policies. Additionally, we extend prior theory to encompass asynchronous and recurrent coagent networks. These extensions facilitate the straightforward design and analysis of hierarchical reinforcement learning algorithms like the option-critic, and eliminate the need for complex derivations of customized learning rules for these algorithms.
Cite
Text
Kostas et al. "Asynchronous Coagent Networks." International Conference on Machine Learning, 2020.Markdown
[Kostas et al. "Asynchronous Coagent Networks." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/kostas2020icml-asynchronous/)BibTeX
@inproceedings{kostas2020icml-asynchronous,
title = {{Asynchronous Coagent Networks}},
author = {Kostas, James and Nota, Chris and Thomas, Philip},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {5426-5435},
volume = {119},
url = {https://mlanthology.org/icml/2020/kostas2020icml-asynchronous/}
}