Texas Hold'em AI 🤖

CS Independent Study @UVa

Overview

This is an independent study on the application of current machine learning techniques into Texas Hold’em AI.

Setup

# Ubuntu/Linux 64-bit
$ sudo apt-get install python-pip python-dev
# Ubuntu/Linux 64-bit, CPU only, Python 3.5
$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.11.0-cp35-cp35m-linux_x86_64.whl

# Mac OS X
$ sudo easy_install pip3
$ sudo easy_install --upgrade six
# Mac OS X, CPU only, Python 3.4 or 3.5:
$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/gpu/tensorflow-0.11.0-py3-none-any.whl


$ sudo pip3 install --upgrade $TF_BINARY_URL

Troubleshoot

Jupyter Notebook documentation

$ pip3 install --upgrade pip
$ pip3 install jupyter
$ jupyter notebook

Demo

Timeline

Resources

Machine Learning
- Framework
  - Awesome TensorFlow Link
  - TensorFlow Playground Link
  - Binary Stochastic Neurons in Tensorflow Link
- Relavant Reports
  - End of Code by Wired
  - Why Randomness is Important for Deep Learning Link
- Book
  - Neural Networks and Deep Learning Link
- Research Paper
  - Deep Reinforcement Learning from Self-Play in Imperfect-Information Games PDF
  - Mastering the Game of Go with Deep Neural Networks and Tree Search PDF
Game Theory
- prisoner dilemma game Link
Behavior Theory
Poker Strategy
- the Poker Bank link
Related Course
- CS221: Artificial Intelligence
- CS6316 Machine Learning
- CS6501 Poker
- AI Strategies for Solving Poker Texas Hold'em Slides
Others' work
- Claudico Overview
- Slumbot
- DeepStack

Acknowledge

Thanks Prof. David Evans for the instructions and supports.

Contact Us

Current Collaborators
- Charlie Wu jw7jb@virginia.edu
- Tong Qiu tq7bw@virginia.edu

Charleo85/Texas-Hold-em-AI