mha-py

This thread is a bit older, but since its pinned here is an idea: What about putting the information, if a move is invalid, into the p array of the...

I think the most important part is the batching of neural network input when predicting p and v. When i ran the othello training, i measured that ~85-90% of the...

That is true... Is it possible to run multiple threads for multiple games plus one thread which calls the prediction of batched states? Like all mcts threads are doing their...

Some pseudo code ```python # MCTS calls: def nnet.predict(board): id = nnet.numQuerys nnet.boards[id] = board nnet.numQuerys += 1 await_nnet_thread_to_do_prediction() return nnet.predictions[id] # NNet thread call: def nnet.compute(): block_treads() while nnet.numQuerys...

I solved it with by replacing `from keras_contrib.layers.normalization import InstanceNormalization, InputSpec` by ``` from keras_contrib.layers.normalization.instancenormalization import InstanceNormalization from keras.layers import InputSpec ``` but im not sure yet if inputspec is...

I think it would be very useful to have the acces to the time inside a njit function! For example, a minmax ai would terminate after a certain time which...