google-deepmind / google-deepmind/acme
Masked actions in MCTS agent
Open
- Dominant language
- Python
- Stars
- 4.1k
- Forks
- 553
- PR merge metrics
- No merged PRs in 30d
Description
I was wondering how actions can get masked in the MCTS agent.
I tried to implement this via an OLT object, but it didn't work.
How do you pass on the information of masked actions in the observation?
Or where can you implement masked actions?
Contributor guide
Assessment
This issue has not been assessed yet.