BSski / mastermind-rl-ddpg

Mastermind Deep Deterministic Policy Gradient (DDPG) solver.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool



WARNING: OLD CODE (06.2021)

This code was written almost a year ago. I have learned a lot since then and I am aware of the poor quality of the code.



Simple Mastermind DDPG solver

MIT License

Table of contents

πŸ“œ Project description

A solver of a simplified Mastermind-like game. Based on Deep Deterministic Policy Gradient (DDPG) algorithm.

πŸ”¨ Technologies used

  • Python 3.7.8
  • OpenAI gym 0.17.2
  • Keras 2.4.3
  • Keras_rl2 1.0.4
  • Matplotlib 3.3.10
  • Tensorflow 2.3.0

⬆️ Room for improvement

This is an old project of mine and it would certainly benefit from:

  • refactoring the code into better functions,
  • refactoring the code into different files,
  • getting rid of many anti-patterns,
  • having tests written for it.

πŸ“ž Contact

πŸ‘· Author

πŸ”“ License

MIT

About

Mastermind Deep Deterministic Policy Gradient (DDPG) solver.

License:MIT License


Languages

Language:Python 100.0%