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

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

Offline reinforcement learning leverages previously collected offline datasets to learn
optimal policies with no necessity to access the real environment. Such a paradigm is also …

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 …

Policy gradient (PG) methods are popular reinforcement learning (RL) methods where a
baseline is often applied to reduce the variance of gradient estimates. In multi-agent RL …

The necessity for cooperation among intelligent machines has popularised cooperative multi-
agent reinforcement learning (MARL) in AI research. However, many research endeavours …

Cooperative multi-agent reinforcement learning (MARL) is making rapid progress for solving
tasks in a grid world and real-world scenarios, in which agents are given different attributes …

This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent
reinforcement learning problem in Markov potential games. It is shown that, under mild …

We study the stationary points and local geometry of gradient play for stochastic games
(SGs), where each agent tries to maximize its own total discounted reward by making …

Exploration-exploitation is a powerful and practical tool in multi-agent learning (MAL);
however, its effects are far from understood. To make progress in this direction, we study a …