An abundance of recent impossibility results establish that regret minimization in Markov
games with adversarial opponents is both statistically and computationally intractable …

We develop a flexible stochastic approximation framework for analyzing the long-run
behavior of learning in games (both continuous and finite). The proposed analysis template …

Policy gradient methods enjoy strong practical performance in numerous tasks in
reinforcement learning. Their theoretical understanding in multiagent settings, however …

Constrained Markov games offer a formal mathematical framework for modeling multi-agent
reinforcement learning problems where the behavior of the agents is subject to constraints …

Designing incentives for an adapting population is a ubiquitous problem in a wide array of
economic applications and beyond. In this work, we study how to design additional rewards …

In this work, we study potential games and Markov potential games under stochastic cost
and bandit feedback. We propose a variant of the Frank-Wolfe algorithm with sufficient …

Cooperative multi-agent reinforcement learning is a powerful tool to solve many real-world
cooperative tasks, but restrictions of real-world applications may require training the agents …

We propose a networked policy gradient play algorithm for solving Markov potential games.
In a Markov game, each agent has a reward function that depends on the actions of all the …

With the increasing deployment of decision-making and learning algorithms in multi-agent
systems, it becomes imperative to understand their efficiency and improve their …

We propose networked policy gradient play for solving Markov potential games including
continuous action and state spaces. In the decentralized algorithm, agents sample their …