AbadIA AlphaZero version

Stay tunned ;-P

Forked from the awesome project:

DeepReinforcementLearning

A replica of the AlphaZero methodology in Python

See this article for a summary of the algorithm and run instructions.

Name		Name	Last commit message	Last commit date
Latest commit History 35 Commits
.ipynb_checkpoints		.ipynb_checkpoints
games		games
run		run
.DS_Store		.DS_Store
.gitignore		.gitignore
AbadiaAgent.py		AbadiaAgent.py
AbadiaGame.py		AbadiaGame.py
LICENSE		LICENSE
MCTS.py		MCTS.py
README-abadia-gym.md		README-abadia-gym.md
README.md		README.md
_config.yml		_config.yml
agent.py		agent.py
config.py		config.py
create_a_mcts.ipynb		create_a_mcts.ipynb
funcs.py		funcs.py
game.py		game.py
gameinfo.ipynb		gameinfo.ipynb
initialise.py		initialise.py
loggers.py		loggers.py
loss.py		loss.py
main.py		main.py
memory.py		memory.py
model.py		model.py
requirements.txt		requirements.txt
run.ipynb		run.ipynb
settings.py		settings.py
utils.py		utils.py