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 …

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

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

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

A unique challenge in Multi-Agent Reinforcement Learning (MARL) is the\emph {curse of
multiagency}, where the description length of the game as well as the complexity of many …

We propose a new model,\emph {independent linear Markov game}, for multi-agent
reinforcement learning with a large state space and a large number of agents. This is a class …

Most existing results about last-iterate convergence of learning dynamics are limited to two-
player zero-sum games, and only apply under rigid assumptions about what dynamics the …

Natural policy gradient has emerged as one of the most successful algorithms for computing
optimal policies in challenging Reinforcement Learning (RL) tasks, yet, very little was known …

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two
common design principles: value decomposition and parameter sharing. A typical MARL …