Problems with Keras/Tensorflow backend

[Andreas Eitel]

Hi,
when trying to run your example, I get a TypeError using the Tensorflow backend.
./run_cem.py --env=Acrobot-v1 --agent=modular_rl.agentzoo.DeterministicAgent --n_iter=2

TypeError: Input 'b' of 'MatMul' Op has type float32_ref that does not match type float64 of argument 'a'.

Do you have an idea how to fix this?
I run everything in a virtual python environment.
Find attached the output of pip list and the error output.
pip_list.txt
log.txt

In my Keras.json I use the default settings: floatx:"float32", backend: "tensorflow"
I am new to tensorflow and to openai, so it might also just be because of that.

Thanks,
Andreas

[Andreas Eitel]

Hi,
it seems to be a problem with the GPU/CUDA 7.5, I was trying to run code on a 980 and it didn't work. Using a TitanX and CUDA 8.0 it works finally.