dqn
dqn copied to clipboard
Does not work with Tensorflow
I get the following error when running with TensorFlow (with GPU)
current context was not created by the StreamExecutor cuda_driver API: 0x2ccf300; a CUDA runtime call was likely performed without using a StreamExecutor context
Issue is that the code is referencing Theano directly:-
from theano.gradient import disconnected_grad
reference:- https://github.com/tensorflow/tensorflow/issues/916
it should be possible to use tf.stop_gradient
to do this. However, this change should ideally belong to Keras backend, so that the DQN code becomes backend-agnostic.
Use K.stop_gradient
?