Hasnain Ali
Results
2
comments of
Hasnain Ali
Hi, I have been facing problems with diagnosing PPO2 training on multiple environments. Especially the episode reward are weird (see the image).  Today, I chanced to read this issue....
> > > @Capitolhill As a quick fix, I suggest trying out [stable-baselines3](https://github.com/DLR-RM/stable-baselines3) which also has tensorboard support and is more actively maintained. Migration from SB2 is mostly as simple...