tambetm/simple_dqn

targets are not really copied when using cpu backend

loofahcus opened this issue · 1 comments

deepqnetwork.py#L133 should be:
targets = preq.asnumpyarray().copy()

Since for cpu backend, asnumpyarray() seems just get the reference of numpy array, which causes the modifications of targets impacting preq.

Thanks @loofahcus! I was aware of this, but forgot to include the fix in this repo.