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

By Nikolai Yakovenko, Liangliang Cao, Colin Raffel, James Fan. 2015

34 citations recorded by the source corpus.

Poker is a family of card games that includes many varia- tions. 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 representa- tion. 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 competi- tive player against human experts. The contributions of this paper include: (1) a novel represen- tation for poker games, extendable to different poker vari- ations, (2) a Convolutional Neural Network (CNN) based learning model that can effectively learn the patterns in three different games, and (3) a self-trained system that signif- icantly beats the heuristic-based program on which it is trained, and our system is competitive against human expert players.

Subfields: Artificial Intelligence, Clinical Psychology, Economics and Econometrics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Clinical Psychology

In Economics and Econometrics

Citations in the corpus

Deep Reinforcement Learning from Self-Play in Imperfect-Information Games (2016, methodology): “Yakovenko et al. (2016) trained deep neural networks in self-play in computer poker, including two poker games that are popular with humans.”
A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning (2017, background): “In our Leduc Poker experiments, we use an alternating implementation that switches periodically between computing the best response (oracle training phase) and meta-strategy learning phase where the empirical payoff tensor is updated and meta-strategy computed.”
Automatic Bridge Bidding Using Deep Reinforcement Learning (2016, methodology): “One line of research on AI for games focuses on full-information games, including chess, Go, and Othello [1], whereas other research considers incomplete information games, such as poker and bridge [2]–[4].”
Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence (2019, background): “Later on, deep multi-agent reinforcement learning (D-MARL) is preferred, due to its scalability, and as it achieves notable advances on two-player turn-based games, such as Poker and Go [61, 85, 106].”