nash_q_learning

nash_q_learning copied to clipboard

Nash Q Learning sample.

The nash q learners solves stateless two-player zero-sum game.

To compute nash strategy, this code uses nashpy.

How to run sample code

1. Install Nashpy

To run sample code, you must install nashpy.

If you haven't installed nashpy, you can install using following command

pip install nashpy

2. Clone this repository

git clone https://github.com/tocom242242/nash_q_learning.git
cd nash_q_learning

3. Run sample matrix game

To run sample code

python run_matrix_game.py

After two-player zero-sum is finished, the program plots result.

blog

https://www.tcom242242.net/entry/2019/07/12/%e3%80%90%e3%83%9e%e3%83%ab%e3%83%81%e3%82%a8%e3%83%bc%e3%82%b8%e3%82%a7%e3%83%b3%e3%83%88%e5%bc%b7%e5%8c%96%e5%ad%a6%e7%bf%92%e3%80%91nash_q_learningnash_q_%e5%ad%a6%e7%bf%92/