Monte-Carlo Search for an Equilibrium in Dec-POMDPs
Yang You, Vincent Thomas, Francis Colas, Olivier Buffet
Abstract
Decentralized partially observable Markov decision processes (Dec-POMDPs) formalize the problem of designing individual controllers for a group of collaborative agents under stochastic dynamics and partial observability. Seeking a global optimum is difficult (NEXP complete), but seeking a Nash equilibrium - each agent policy being a best response to the other agents - is more accessible, and allowed addressing infinite-horizon problems with solutions in the form of finite state controllers. In this paper, we show that this approach can be adapted to cases where only a generative model (a simulator) of the Dec-POMDP is available. This requires relying on a simulation-based POMDP solver to construct an agent’s FSC node by node. A related process is used to heuristically derive initial FSCs. Experiment with benchmarks shows that MC-JESP is competitive with existing Dec-POMDP solvers, even better than many offline methods using explicit models.
BibTeX
@InProceedings{pmlr-v216-you23a,
title = {Monte-{C}arlo Search for an Equilibrium in {Dec-POMDPs}},
author = {You, Yang and Thomas, Vincent and Colas, Francis and Buffet, Olivier},
booktitle = {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence},
pages = {2444--2453},
year = {2023},
editor = {Evans, Robin J. and Shpitser, Ilya},
volume = {216},
series = {Proceedings of Machine Learning Research},
month = {31 Jul--04 Aug},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v216/you23a/you23a.pdf},
url = {https://proceedings.mlr.press/v216/you23a.html},
abstract = {Decentralized partially observable Markov decision processes (Dec-POMDPs) formalize the problem of designing individual controllers for a group of collaborative agents under stochastic dynamics and partial observability. Seeking a global optimum is difficult (NEXP complete), but seeking a Nash equilibrium - each agent policy being a best response to the other agents - is more accessible, and allowed addressing infinite-horizon problems with solutions in the form of finite state controllers. In this paper, we show that this approach can be adapted to cases where only a generative model (a simulator) of the Dec-POMDP is available. This requires relying on a simulation-based POMDP solver to construct an agent’s FSC node by node. A related process is used to heuristically derive initial FSCs. Experiment with benchmarks shows that MC-JESP is competitive with existing Dec-POMDP solvers, even better than many offline methods using explicit models.}
}