google-deepmind / google-deepmind/open_x_embodiment
sub-optimal
Open
- Dominant language
- Jupyter Notebook
- Stars
- 2k
- Forks
- 127
- PR merge metrics
- No merged PRs in 30d
Description
There are some datasets that have sub-optimal trajectories (e.g. maniskill, bridge). However, I found the total reward of all trajectories are same (i.e. 1). Is there anything wrong?
And is there any way to split the sub-optimal trajectories?
Contributor guide
Assessment
This issue has not been assessed yet.