Online Learning in Unknown Markov Games [article]

Yi Tian, Yuanhao Wang, Tiancheng Yu, Suvrit Sra
2021 arXiv   pre-print
We study online learning in unknown Markov games, a problem that arises in episodic multi-agent reinforcement learning where the actions of the opponents are unobservable. We show that in this challenging setting, achieving sublinear regret against the best response in hindsight is statistically hard. We then consider a weaker notion of regret by competing with the minimax value of the game, and present an algorithm that achieves a sublinear 𝒪̃(K^2/3) regret after K episodes. This is the first
more » ... ublinear regret bound (to our knowledge) for online learning in unknown Markov games. Importantly, our regret bound is independent of the size of the opponents' action spaces. As a result, even when the opponents' actions are fully observable, our regret bound improves upon existing analysis (e.g., (Xie et al., 2020)) by an exponential factor in the number of opponents.
arXiv:2010.15020v2 fatcat:w6u272f33jg7fpq4gi4pnolmuu