Karl Pertsch

Hi! If you check the dataset you can see that the goal is always constant, so we decided to just keep it as part of the input (the environment also...

Hi! Thanks for raising this issue! I have not run this comparison before so I can't tell you why exactly you are observing such different outcomes. Generally, small implementation details...

I am not sure why this is happening. Two things you could check: (1) did you use Q-target clipping during training? Using this clipping can stabilize training by avoiding very...

Hey sorry, I missed this issue when you raised it -- is this question still relevant?

Hi Ce, Not sure whether this is still a problem since you closed the issue, but we're just using the default kitchen dataset provided by D4RL -- you can see...

Hi Ce, Yes, it's straightforward to change the task in the Kitchen environment. You can define new versions of the Kitchen environment with different target tasks like here: https://github.com/kpertsch/d4rl/blob/21743171daf2094379b91dfb74bf7c15049b729f/d4rl/kitchen/kitchen_envs.py#L132 Then...

Hi! This is a bit odd -- can you build other d4rl environments after importing d4rl? did you import the d4rl package before calling gym.make(...)? Importing the package is important...

Hi! Sorry for the late reply, I missed this issue and just came across it! I suspect that the error you are encountering is not specific to the SPiRL codebase....