This paper surveys the field of deep multiagent reinforcement learning (RL). The
combination of deep neural networks with RL has gained increased traction in recent years …

There has been a resurgence of interest in multiagent reinforcement learning (MARL), due
partly to the recent success of deep neural networks. The simplest form of MARL is …

Many real-world applications can be described as large-scale games of imperfect
information. To deal with these challenging domains, prior work has focused on computing …

Abstract Counterfactual Regret Minimization (CFR) is the leading algorithm for solving large
imperfect-information games. It converges to an equilibrium by iteratively traversing the …

A fundamental challenge in imperfect-information games is that states do not have well-
defined values. As a result, depth-limited search algorithms used in single-agent settings …

Decomposition, ie independently analyzing possible subgames, has proven to be an
essential principle for effective decision-making in perfect information games. However, in …

The deep policy gradient method has demonstrated promising results in many large-scale
games, where the agent learns purely from its own experience. Yet, policy gradient methods …

Online search in games has been a core interest of artificial intelligence. Search in imperfect
information games (eg, Poker, Bridge, Skat) is particularly challenging due to the …

The leading approach for solving large imperfect-information games is automated
abstraction followed by running an equilibrium-finding algorithm. We introduce a distributed …

Most real-world games and many recreational games are games of incomplete information.
Over the last dozen years, abstraction has emerged as a key enabler for solving large …