Dominik Brunmeir dd3eb11ea8 | ||
---|---|---|
.gitignore | ||
Player.py | ||
State.py | ||
main.py | ||
readme.md |
readme.md
Tic Tac Toe
A simple game of tic tac toe
Q-Learning example as part of the asim reinforcement learning tutorial. the agent (player) learns not to lose the game, given sufficiently long training period.