Antonin RAFFIN
Antonin RAFFIN
Hello, could you be more specific on which algo/env you are using ?
> I am using the qrdqn algo and a custom environment based on top of the minigrid env Could you share the observation and action spaces? You are probably missing...
You are probably either missing image pre-processing (dividing by 255 before feeding to the network) or are not comparing to the greedy policy. The following works and was tested comparing...
Hello, > didn't remove environments I didn't run (e.g. Ant). Still error message could be more clear, or better empty folders could be skipped. yes, that's probably the case, you...
> Hi, can I try to solve this ? yes you can =)
> Since gym 0.21.0 you can pass : to gym.make() to make it automatically import the given package. Interesting... I didn't know about that undocumented feature. Yes, makes sense then...
> To explain in some more detail how it works: if you do gym.make("module_name:envid-v0"), then internally it gets split on the colon into module_name and envid-v0. Internally then it calls...
We will also have another problem: https://github.com/DLR-RM/rl-baselines3-zoo/blob/660f2d354ef9d63cd7a478390780dffa0cadb80c/rl_zoo3/train.py#L161-L171 EDIT: we can skip that check when `module:env-id` is passed.
You should be able to work with them but mujoco installation for v2 is harder and you will need to update the names in the yaml files.
gym is no longer supported since https://github.com/DLR-RM/rl-baselines3-zoo/pull/403 so i would recommend you to update the env to gymnasium and do a pull request to the gym donkey car repo so...