tansey/linear_ttt
A framework for experimenting with different linear function approximators with gradient-descent Sarsa(lambda) following an epsilon-greedy policy in Tic-Tac-Toe.
Python
Stargazers
No one’s star this repository yet.
A framework for experimenting with different linear function approximators with gradient-descent Sarsa(lambda) following an epsilon-greedy policy in Tic-Tac-Toe.
Python
No one’s star this repository yet.