Super-mario-bros-A3C-pytorch
Super-mario-bros-A3C-pytorch copied to clipboard
How should I continue my training?
When I interrupted my last training, How should I continue my training? Otherwise, once I start training, I can't stop.
Hi, Train a model for a single level should not take too much time. Hence I didnt write a script for resuming training phase. But you could try to do it, since it is not too complicated.
hey, the way i do it is when developing, I run it in a jupyter notebook. You can just interrupt the kernel, save the weights, and rerun that particular cell. It'd just pick out the most recently updated weights, as long as the policy/agent object is declared globally.