• Corpus ID: 44036858

NN-based Poker Hand Classification and Game Playing

@inproceedings{Bhat2016NNbasedPH,
  title={NN-based Poker Hand Classification and Game Playing},
  author={Gautam Shreedhar Bhat},
  year={2016}
}
  • G. Bhat
  • Published 2016
  • Economics, Computer Science
Poker is a family of complex card games, each with a different set of rules. In our project, we utilize a simplified version of Texas Hold’em poker to build and train a poker bot that learns to classify hands and devises a playing strategy in order to be competitive player. We developed a system that uses a fully-connected neural network that can be trained to understand the patterns between the cards and the hands that can be formed from those cards. Thus, the trained neural network can be the… 
gautambhat.github.io
2 Citations
Background Citations
1

Figures from this paper

2 Citations

Citation Type

Citation Type

Opponent Modeling in Poker Games
TLDR
This paper study mixed-method opponent modeling, one is Bayesian probabilistic model, one was the neural network (NN)-based prediction model, and the last is opponent type identifying model, which combines these three methods to generate an integrated agent for opponent modeling.
Applying Machine Learning to a Conventional Data Processing Task: A Quantitative Evaluation
TLDR
This paper shows how an accuracy of 100% can be achieved for assessing poker hands according to Texas Hold'em rules, with a small set of labeled training data compared to the number of possible hands.

References

SHOWING 1-4 OF 4 REFERENCES
Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games Using Convolutional Networks
TLDR
A novel representation for poker games, extendable to different poker variations, a Convolutional Neural Network (CNN) based learning model that can effectively learn the patterns in three different games, and a self-trained system that significantly beats the heuristic-based program on which it is trained.
Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
TLDR
This paper introduces the first scalable end-to-end approach to learning approximate Nash equilibria without prior domain knowledge, and combines fictitious self-play with deep reinforcement learning.
Evolutionary Data Mining With Automatic Rule Generalization
TLDR
RAGA, a data mining system that combines evolutionary and symbolic machine learning methods, is described and recent extensions required to extract comprehensible and strong rules from a very challenging dataset are discussed.
UCI Machine Learning Repository [http://archive.ics.uci.edu/ml
  • University of California, School of Information and Computer Science,
  • 2013