AlbaTablut

Implementation of a Reinforcement Learning agent for the game of Tablut; in particular, implemented AlphaGo Zero but for the game of Tablut.

Name		Name	Last commit message	Last commit date
Latest commit History 15 Commits
TablutRL		TablutRL
ckpts		ckpts
data		data
lightning_logs		lightning_logs
wandb		wandb
.gitignore		.gitignore
AI.py		AI.py
AlbaTablut presentation.pdf		AlbaTablut presentation.pdf
AlphaZeroNet.py		AlphaZeroNet.py
Board.py		Board.py
Piece.py		Piece.py
README.md		README.md
Square.py		Square.py
TODO.md		TODO.md
conversions.py		conversions.py
data_handler.py		data_handler.py
main.py		main.py
requirements.txt		requirements.txt
tempCodeRunnerFile.py		tempCodeRunnerFile.py
test.py		test.py
train.py		train.py
train_data.py		train_data.py
unibo_competition.py		unibo_competition.py
utils.py		utils.py

Provide feedback