DeepAI AI Chat
Log In Sign Up

Single Deep Counterfactual Regret Minimization

01/22/2019
by   Eric Steinberger, et al.
0

Counterfactual Regret Minimization (CFR) is the most successful algorithm for finding approximate Nash equilibria in imperfect information games. However, CFR's reliance on full game-tree traversals limits its scalability. For this reason, the game's state- and action-space is often abstracted (i.e. simplified) for CFR, and the resulting strategy is then translated back to the full game, which requires extensive expert-knowledge and often converges to highly exploitable policies. A recently proposed method, Deep CFR, applies deep learning directly to CFR, allowing the agent to intrinsically abstract and generalize over the state-space from samples, without requiring expert knowledge. In this paper, we introduce Single Deep CFR (SD-CFR), a simplified variant of Deep CFR that has a lower overall approximation error by avoiding the training of an average strategy network. We show that SD-CFR is more attractive from a theoretical perspective and empirically outperforms Deep CFR in head-to-head matches of a large poker game.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/26/2021

NNCFR: Minimize Counterfactual Regret with Neural Networks

Counterfactual Regret Minimization (CFR) is the popular method for findi...
11/01/2018

Deep Counterfactual Regret Minimization

Counterfactual Regret Minimization (CFR) is the leading algorithm for so...
07/20/2020

Unlocking the Potential of Deep Counterfactual Value Networks

Deep counterfactual value networks combined with continual resolving pro...
12/27/2018

Double Neural Counterfactual Regret Minimization

Counterfactual Regret Minimization (CRF) is a fundamental and effective ...
04/11/2022

A Unified Perspective on Deep Equilibrium Finding

Extensive-form games provide a versatile framework for modeling interact...
09/11/2018

Solving Imperfect-Information Games via Discounted Regret Minimization

Counterfactual regret minimization (CFR) is a family of iterative algori...
06/08/2022

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Recent techniques for approximating Nash equilibria in very large games ...