COG-DICE: An Algorithm for Solving Continuous-Observation Dec-POMDPs
Abstract
The decentralized partially observable Markov decision process (Dec-POMDP) is a powerful model for representing multi-agent problems with decentralized behavior. Unfortunately, current Dec-POMDP solution methods cannot solve problems with continuous observations, which are common in many real-world domains. To that end, we present a framework for representing and generating Dec-POMDP policies that explicitly include continuous observations. We apply our algorithm to a novel tagging problem and an extended version of a common benchmark, where it generates policies that meet or exceed the values of equivalent discretized domains without the need for finding an adequate discretization.
Cite
Text
Clark-Turner and Amato. "COG-DICE: An Algorithm for Solving Continuous-Observation Dec-POMDPs." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/638Markdown
[Clark-Turner and Amato. "COG-DICE: An Algorithm for Solving Continuous-Observation Dec-POMDPs." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/clarkturner2017ijcai-cog/) doi:10.24963/IJCAI.2017/638BibTeX
@inproceedings{clarkturner2017ijcai-cog,
title = {{COG-DICE: An Algorithm for Solving Continuous-Observation Dec-POMDPs}},
author = {Clark-Turner, Madison and Amato, Christopher},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {4573-4579},
doi = {10.24963/IJCAI.2017/638},
url = {https://mlanthology.org/ijcai/2017/clarkturner2017ijcai-cog/}
}