mirror_of_important_repositories
/
github.com__longyangking__AlphaFiveormore
mirror of https://github.com/longyangking/AlphaFiveormore
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
Play "Five or More" game with Artificial intelligence
12 Commits
1 Branch
0 Tags
68 KiB
Python 100%
 
Go to file
Yang Long aef9044e0e test 2019-06-12 12:00:38 +08:00
alphafiveormore fix game bugs and update README 2018-12-04 16:35:28 +08:00
pics basic UI structure 2018-11-10 14:42:38 +08:00
.gitignore Fix UI bugs 2018-12-03 20:59:02 +08:00
LICENSE Initial commit 2018-10-26 16:46:26 +08:00
README.md test 2019-06-12 12:00:38 +08:00

README.md

AlphaFiveormore

Play "Five or More" game with Artificial intelligence

Features

  • Home-made "Five or More" game
  • Curiosity-driven Exploration by Self-supervised Prediction [1,2]

How to use

  • Play "Five or more" game by yourself

      cd alphafiveormore
  python alphafiveormore.py --playai

  • Re-train a new AI model

      cd alphafiveormore
  python alphafiveormore.py --retrain --verbose

  • Continue to train the AI model

      cd alphafiveormore
  python alphafiveormore.py --train --verbose

  • View the AI model to play game

      cd alphafiveormore
  python alphafiveormore.py --playai --verbose

Press key Space to evaluate the step

Status

GameEngine is currently inadequate. Working on it

References

  1. Pathak, Deepak, et al. "Curiosity-driven exploration by self-supervised prediction." International Conference on Machine Learning (ICML). Vol. 2017. 2017.
  2. Achiam, Joshua, and Shankar Sastry. "Surprise-based intrinsic motivation for deep reinforcement learning." arXiv preprint arXiv:1703.01732 (2017).

E-mail

longyang_123@yeah.net
You're most welcome to contact with me to discuss any details about this project