We examine global non-asymptotic convergence properties of policy gradient methods for
multi-agent reinforcement learning (RL) problems in Markov potential games (MPGs). To …

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 …

A major challenge of multiagent reinforcement learning (MARL) is the curse of multiagents,
where the size of the joint action space scales exponentially with the number of agents. This …

Reinforcement learning (RL) has recently achieved tremendous successes in many artificial
intelligence applications. Many of the forefront applications of RL involve multiple agents …

We show that computing approximate stationary Markov coarse correlated equilibria (CCE)
in general-sum stochastic games is PPAD-hard, even when there are two players, the game …

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 …

We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement
learning from human feedback. Our approach is minimalist in that it does not require training …

We study infinite-horizon discounted two-player zero-sum Markov games, and develop a
decentralized algorithm that provably converges to the set of Nash equilibria under self-play …

The use of min-max optimization in the adversarial training of deep neural network
classifiers, and the training of generative adversarial networks has motivated the study of …

Multi-agent reinforcement learning (MARL) algorithms often suffer from an exponential
sample complexity dependence on the number of agents, a phenomenon known as the …