MarcellusZhao/PyTorch-Tic-Tac-Toe
Project for CS-456 Artificial neural networks/reinforcement learning @ EPFL: PyTorch implementation of Q-Learning and Deep Q-Learning to make agents play Tic-Tac-Toe.
Jupyter Notebook
Project for CS-456 Artificial neural networks/reinforcement learning @ EPFL: PyTorch implementation of Q-Learning and Deep Q-Learning to make agents play Tic-Tac-Toe.
Jupyter Notebook