google-deepmind / google-deepmind/constrained_optidice
Why only cost value function of initial state
Open
- Dominant language
- Python
- Stars
- 10
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
Hi
Why did you consider here only cost value function of initial state ?
What if other states are bigger than the cost threshold ?
https://github.com/deepmind/constrained_optidice/blob/ddddbc768d7e7c8fde6a2200e1764c095bbc2b1f/tabular/mdp_util.py#L182
Contributor guide
Assessment
This issue has not been assessed yet.