We study a new class of Markov games,\textit {(multi-player) zero-sum Markov Games} with
{\it Networked separable interactions}(zero-sum NMGs), to model the local interaction …

We study Markov potential games under the infinite horizon average reward criterion. Most
previous studies have been for discounted rewards. We prove that both algorithms based on …

Constrained Markov games offer a formal mathematical framework for modeling multi-agent
reinforcement learning problems where the behavior of the agents is subject to constraints …

Independent learning (IL), despite being a popular approach in practice to achieve
scalability in large-scale multi-agent systems, usually lacks global convergence guarantees …

We design a multi-agent and networked policy gradient algorithm in Markov potential
games. Each agent has its own rewards and utility as functions of joint actions and a shared …

This paper proposes a new framework of Markov $\alpha $-potential games to study Markov
games. In this new framework, Markov games are shown to be Markov $\alpha $-potential …

Markov games offer a formal mathematical framework for modeling multi-agent
reinforcement learning problems. Markov Potential Games (MPGs) represent a subclass of …