weidler / RLaSpa

Reinforcement Learning in Latent Space
MIT License
5 stars 1 forks source link

Create statistics of training time and performance #19

Closed HansBambel closed 5 years ago

HansBambel commented 5 years ago

In order to compare our different approaches we need to collect statistics of the training.

dannigt commented 5 years ago

@weidler, is it ok that I make learn_batch_of_tuples in representation return the batch loss instead None? Would make it much easier for logging.

HansBambel commented 5 years ago

Isn't this done already?