Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games

by   Stefanos Leonardos, et al.

Potential games are arguably one of the most important and widely studied classes of normal form games. They define the archetypal setting of multi-agent coordination as all agent utilities are perfectly aligned with each other via a common potential function. Can this intuitive framework be transplanted in the setting of Markov Games? What are the similarities and differences between multi-agent coordination with and without state dependence? We present a novel definition of Markov Potential Games (MPG) that generalizes prior attempts at capturing complex stateful multi-agent coordination. Counter-intuitively, insights from normal-form potential games do not carry over as MPGs can consist of settings where state-games can be zero-sum games. In the opposite direction, Markov games where every state-game is a potential game are not necessarily MPGs. Nevertheless, MPGs showcase standard desirable properties such as the existence of deterministic Nash policies. In our main technical result, we prove fast convergence of independent policy gradient to Nash policies by adapting recent gradient dominance property arguments developed for single agent MDPs to multi-agent learning settings.



There are no comments yet.


page 1

page 2

page 3

page 4


Policy-Gradient Algorithms Have No Guarantees of Convergence in Continuous Action and State Multi-Agent Settings

We show by counterexample that policy-gradient algorithms have no guaran...

Gradient Play in Multi-Agent Markov Stochastic Games: Stationary Points and Convergence

We study the performance of the gradient play algorithm for multi-agent ...

Independent Natural Policy Gradient Always Converges in Markov Potential Games

Multi-agent reinforcement learning has been successfully applied to full...

On the Effect of Log-Barrier Regularization in Decentralized Softmax Gradient Play in Multiagent Systems

Softmax policy gradient is a popular algorithm for policy optimization i...

Newton-based Policy Optimization for Games

Many learning problems involve multiple agents optimizing different inte...

Independent Natural Policy Gradient Methods for Potential Games: Finite-time Global Convergence with Entropy Regularization

A major challenge in multi-agent systems is that the system complexity g...

Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality

The interplay between exploration and exploitation in competitive multi-...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.