Deep Counterfactual Regret Minimization
This addresses the challenge of automating equilibrium computation in complex games for AI and game theory, representing a novel advancement beyond tabular methods.
The paper tackles the problem of solving large imperfect-information games like poker by introducing Deep Counterfactual Regret Minimization, which eliminates the need for manual abstraction by using deep neural networks to approximate CFR behavior, achieving strong performance in large poker games.
Counterfactual Regret Minimization (CFR) is the leading framework for solving large imperfect-information games. It converges to an equilibrium by iteratively traversing the game tree. In order to deal with extremely large games, abstraction is typically applied before running CFR. The abstracted game is solved with tabular CFR, and its solution is mapped back to the full game. This process can be problematic because aspects of abstraction are often manual and domain specific, abstraction algorithms may miss important strategic nuances of the game, and there is a chicken-and-egg problem because determining a good abstraction requires knowledge of the equilibrium of the game. This paper introduces Deep Counterfactual Regret Minimization, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game. We show that Deep CFR is principled and achieves strong performance in large poker games. This is the first non-tabular variant of CFR to be successful in large games.