Ionel Hosu

Evaluation functions missing

1

What happened to the evaluation code in the last version? Is evaluation not covered any more by this package? There is a discrepancy between the current version and the documentation....

Training slowing down dramatically

1

Did anyone face the issue of the training process slowing down? For example, training one DQN-CTS worker on Montezuma's Revenge runs at about 220 iter/sec after 100.000 steps and 35...

Reproducing the results

1

Hi, Congratulations on your results! I have a couple of questions about your code: 1. How much time did the training on 128 GPUs take? 2. Is there any chance...