Would you be comfortable with me adding optional TensorFlow support to the library?
The current algorithms are deterministic in nature; so using a neural reinforcement learning algorithm is a bit out of the current scope. But easyAI's simple and easy TwoPlayerGame framework could make using TensorFlow far easier for programmers new to AI.
I'd envision writing a tf_learn function that repeatably has the AI play itself, randomly choosing moves at first, and then learning from each iteration. The result would be a checkpoint file that contains the decisions that would be used during a play of TwoPlayerGame with the TensorFlowModel AI. If an entry is found in the (optional) transposition table, it is used first, otherwise the model checkpoint file is used to make a decision.
@Zulko
Would you be comfortable with me adding optional TensorFlow support to the library?
The current algorithms are deterministic in nature; so using a neural reinforcement learning algorithm is a bit out of the current scope. But easyAI's simple and easy
TwoPlayerGameframework could make using TensorFlow far easier for programmers new to AI.I'd envision writing a
tf_learnfunction that repeatably has the AI play itself, randomly choosing moves at first, and then learning from each iteration. The result would be acheckpointfile that contains the decisions that would be used during a play ofTwoPlayerGamewith theTensorFlowModelAI. If an entry is found in the (optional) transposition table, it is used first, otherwise the model checkpoint file is used to make a decision.Thoughts?