UltimateTicTacToe

Agents trained for TicTacToe variations using Reinforcement learning algorithms

Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
agent		agent
game		game
utils		utils
README.md		README.md
agent_o_model.pth_W1.npy		agent_o_model.pth_W1.npy
agent_o_model.pth_W2.npy		agent_o_model.pth_W2.npy
agent_o_model.pth_b1.npy		agent_o_model.pth_b1.npy
agent_o_model.pth_b2.npy		agent_o_model.pth_b2.npy
agent_x_model.pth_W1.npy		agent_x_model.pth_W1.npy
agent_x_model.pth_W2.npy		agent_x_model.pth_W2.npy
agent_x_model.pth_b1.npy		agent_x_model.pth_b1.npy
agent_x_model.pth_b2.npy		agent_x_model.pth_b2.npy
config.py		config.py
play.py		play.py
train.py		train.py

Provide feedback