Richard Jozsa
Richard Jozsa
I have also met the same issue, that if I use Maskable PPO, I can not use `SubProvVecEnv` with it, same error showing up.
For me same error happens, and with @CristoJV method theoratically should work. Error message: ``` ens5 | Process ForkServerProcess-1: ens5 | Process ForkServerProcess-2: ens5 | Traceback (most recent call last):...
@CristoJV can you patch it up somehow? in a PR or something? I just want to confirm that it also works for me for example.
@RemiG3 hey, have you started to implement it? Mayba I can give a free hand in it :)
I have came accross on this, this is quite modular and easy to tune, [Transformers-RL](https://github.com/dhruvramani/Transformers-RL), the only backside is that, it has been implemented only to gaussian policy.
Just a comment, I've tested this implementation with QR-DQN with Vecenv multiple environment but it fails because of the missing part. But good job to start the work on it!...
Hey @araffin , it is great to hear that. Does SBX/Jax means this much speed improvement? If you think it is ready for testing I can give a try, just...
When I tested this PR I also noticed an explosion in loss, in that time I felt that it is because of the tweaking here and there. and I also...
Hey everyone, I have tried the code what @emrul pasted in the IQN PR comments, it works. One thing what I haven't got to work is the SubProcEenv wrapping. Just...
This is the error what I got, but if it works for you than I recheck. I use a customenv maybe that caused something. Traceback (most recent call last): RLTEST...