Recent theoretical work studies sample-efficient reinforcement learning (RL) extensively in
two settings: learning interactively in the environment (online RL), or learning from an offline …

We obtain global, non-asymptotic convergence guarantees for independent learning
algorithms in competitive reinforcement learning settings with two agents (ie, zero-sum …

Abstract Model-based algorithms—algorithms that explore the environment through building
and utilizing an estimated model—are widely used in reinforcement learning practice and …

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 …

Multi-agent reinforcement learning has made substantial empirical progresses in solving
games with a large number of players. However, theoretically, the best known sample …

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 …

Abstract Model-based reinforcement learning (RL), which finds an optimal policy using an
empirical model, has long been recognized as one of the cornerstones of RL. It is especially …

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 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 …