Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games

TL;DR

This paper introduces Poker-CNN, a unified pattern learning system using convolutional neural networks that learns to play various poker games through self-play, achieving competitive performance against humans without domain-specific knowledge.

Contribution

The paper presents a novel poker representation, a CNN-based learning model applicable to multiple poker variants, and a self-training approach that surpasses heuristic programs and competes with human experts.

Findings

Successfully learned patterns in three different poker games.

Outperformed heuristic-based programs in all tested games.

Achieved competitive results against human expert players.

Abstract

Poker is a family of card games that includes many variations. We hypothesize that most poker games can be solved as a pattern matching problem, and propose creating a strong poker playing system based on a unified poker representation. Our poker player learns through iterative self-play, and improves its understanding of the game by training on the results of its previous actions without sophisticated domain knowledge. We evaluate our system on three poker games: single player video poker, two-player Limit Texas Hold'em, and finally two-player 2-7 triple draw poker. We show that our model can quickly learn patterns in these very different poker games while it improves from zero knowledge to a competitive player against human experts. The contributions of this paper include: (1) a novel representation for poker games, extendable to different poker variations, (2) a CNN based learning model that can effectively learn the patterns in three different games, and (3) a self-trained system that significantly beats the heuristic-based program on which it is trained, and our system is competitive against human expert players.