Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1645-1650.
Abstract
Nowadays, multiagent planning under uncertainty scales to tens or even hundreds of agents. However, current methods either are restricted to problems with factored value functions, or provide solutions without any guarantees on quality. Methods in the former category typically build on heuristic search using upper bounds on the value function. Unfortunately, no techniques exist to compute such upper bounds for problems with non-factored value functions, which would additionally allow for meaningful benchmarking of methods of the latter category. To mitigate this problem, this paper introduces a family of influence-optimistic upper bounds for factored Dec-POMDPs without factored value functions. We demonstrate how we can achieve firm quality guarantees for problems with hundreds of agents.
@inproceedings{ijcai2015p235,
title = {Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions},
author = {Oliehoek, Frans A. and Spaan, Matthijs T. J. and Witwicki, Stefan J.},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {1645--1650},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/235},
}
TY - CPAPER TI - Factored Upper Bounds for Multiagent Planning Problems under Uncertainty with Non-Factored Value Functions AU - Oliehoek, Frans A. AU - Spaan, Matthijs T. J. AU - Witwicki, Stefan J. T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 1645 EP - 1650 UR - https://ijcai.org/proceedings/2015/235 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: