Average-Reward Decentralized Markov Decision Processes
Proceedings of the Twentieth International Joint Conference on Artificial Intelligence. Pages 1997-2001.
Abstract
Formal analysis of decentralized decision making has become a thriving research area in recent years, producing a number of multi-agent extensions of Markov decision processes. While much of the work has focused on optimizing discounted cumulative reward, optimizing average reward is sometimes a more suitable criterion. We formalize a class of such problems and analyze its characteristics, showing that it is NP complete and that optimal policies are deterministic. Our analysis lays the foundation for designing two optimal algorithms. Experimental results with a standard problem from the literature illustrate the applicability of these solution techniques.
@inproceedings{ijcai2007p322,
title = {Average-Reward Decentralized Markov Decision Processes},
author = {Petrik, Marek and Zilberstein, Shlomo},
booktitle = {Proceedings of the Twentieth International Joint Conference on
Artificial Intelligence, {IJCAI-07}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ramon López de Mántaras},
pages = {1997--2001},
year = {2007},
url = {https://ijcai.org/proceedings/2007/322},
}
TY - CPAPER TI - Average-Reward Decentralized Markov Decision Processes AU - Petrik, Marek AU - Zilberstein, Shlomo T2 - Proceedings of the Twentieth International Joint Conference on Artificial Intelligence, IJCAI-07 PB - International Joint Conferences on Artificial Intelligence PY - 2007 SP - 1997 EP - 2001 UR - https://ijcai.org/proceedings/2007/322 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
