AAAI 2026technical0 citations
Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions
Reda Ouhamma, Maryam Kamgarpour
Abstract
We address payoff-based decentralized learning in infinite-horizon zero-sum Markov games. In this setting, each player makes decisions based solely on received rewards, without observing the opponent
BibTeX
@inproceedings{aaai2026_learninginzerosu,
title = {Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions},
author = {Reda Ouhamma and Maryam Kamgarpour},
booktitle = {AAAI 2026},
year = {2026}
}