Related papers: Decentralized Q-Learning in Zero-sum Markov Games

Decentralized Q-Learning in Zero-sum Markov Games

URL: http://arxiv.org/abs/2106.02748v1
Date: Fri, 4 Jun 2021 22:42:56 GMT
Title: Decentralized Q-Learning in Zero-sum Markov Games
Authors: Muhammed O. Sayin, Kaiqing Zhang, David S. Leslie, Tamer Basar, Asuman Ozdaglar
Abstract summary: We study multi-agent reinforcement learning (MARL) in discounted zero-sum Markov games. We develop for the first time a radically uncoupled Q-learning dynamics that is both rational and convergent. The key challenge in this decentralized setting is the non-stationarity of the learning environment from an agent's perspective.
Score: 33.81574774144886
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We study multi-agent reinforcement learning (MARL) in infinite-horizon discounted zero-sum Markov games. We focus on the practical but challenging setting of decentralized MARL, where agents make decisions without coordination by a centralized controller, but only based on their own payoffs and local actions executed. The agents need not observe the opponent's actions or payoffs, possibly being even oblivious to the presence of the opponent, nor be aware of the zero-sum structure of the underlying game, a setting also referred to as radically uncoupled in the literature of learning in games. In this paper, we develop for the first time a radically uncoupled Q-learning dynamics that is both rational and convergent: the learning dynamics converges to the best response to the opponent's strategy when the opponent follows an asymptotically stationary strategy; the value function estimates converge to the payoffs at a Nash equilibrium when both agents adopt the dynamics. The key challenge in this decentralized setting is the non-stationarity of the learning environment from an agent's perspective, since both her own payoffs and the system evolution depend on the actions of other agents, and each agent adapts their policies simultaneously and independently. To address this issue, we develop a two-timescale learning dynamics where each agent updates her local Q-function and value function estimates concurrently, with the latter happening at a slower timescale.