You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I've run the script in training mode, and even after the training was over, if I then run it in test or render mode I was given the "no saved model" message. How do I make it save the model? And how do I render the (saved and learned) policy only once the training is over? Thanks in advance for your time!
The text was updated successfully, but these errors were encountered:
Models are saved every 2mm frames by default (https://github.com/greydanus/baby-a3c/blob/master/baby-a3c.py#L127-L129). Make sure models are being saved, when training. The saving process will create a folder with the name of the environment and a log.txt at the top (just like in the repo breakout-v4, pong-v4, spaceinvaders-v4, etc. An additional thing to verify is that you are running the script from the top directory (e.g.: python baby-a3c.py --env Pong-v0 --test). If you run it from other paths it might not work.
Give it a try: python baby-a3c.py --env Pong-v0 --test from the project's root should work.
Hi, I've run the script in training mode, and even after the training was over, if I then run it in test or render mode I was given the "no saved model" message. How do I make it save the model? And how do I render the (saved and learned) policy only once the training is over? Thanks in advance for your time!
The text was updated successfully, but these errors were encountered: