Ankur Handa

Results 22 comments of Ankur Handa

@ViktorM @Denys88 the example above assumes that you are using a frozen network. You can't optimise the weights of this network because `rl_games` has `torch.infernce()` context for doing running mean...

As long as you don't do anything to the CNN, you should be fine. Normalizing `x` should be OK. My main concern is if you want to do end-to-end optimising...