JustinS

I tried with the new commit, but the same problem still appears. There are a lot of other compatibility issues as well, all of them due to Arena and mlagents...

Thanks for getting back to me so soon! Posting the code would be difficult, since it includes some proprietary elements. However, if there is any chance that you would be...

Just a quick update, I tried creating a dataset with the empty minigrid environment, just to see if the problem was with my custom environment. When I tried to create...

Here is a toy example of what I am trying to do: ``` import os import gymnasium as gym import numpy as np from minigrid.wrappers import * import minari from...

@younik Thank you very much for getting back to me about that! Are there any examples of how to overwrite the observation space for the DataCollector and replace the mission...

Thank you very much! I think that part of the code might be fixed. My implementation now looks like this ``` import os import gymnasium as gym import numpy as...

Thank you very much! That fixes the problem, except for one small issue. I am also trying to save and load the timestep number of each step the agent takes,...

> Hey @JustinS6626, are you installing pennylane-qulacs into the same Python environment as the run that already had Qulacs GPU installed? Thanks for getting back to me again! Yes, that's...

It looks like it could be an issue in the installation script. Is there anything you can do about that?

Thanks again for getting back to me! Using the workaround mentioned on the qulacs github, I managed to install `qulacs-gpu` on its own from source, but now when I try...