Closed barrybecker4 closed 6 years ago
Currently its tied to tic tac toe, but it does not need to be. Tic tac toe can be used as an example in the tests, but q-learning itself should be a completely generic reinforcement learning strategy that can be applied to a variety of domains.
Just did this. Common Q-learning is in qlearning/common. The TicTacToe implementation provides and example of how it can be used.
Currently its tied to tic tac toe, but it does not need to be. Tic tac toe can be used as an example in the tests, but q-learning itself should be a completely generic reinforcement learning strategy that can be applied to a variety of domains.