google-deepmind / google-deepmind/acme
Is it possible to run mompo for discrete and continuous action spaces?
Open
- Dominant language
- Python
- Stars
- 4.1k
- Forks
- 553
- PR merge metrics
- No merged PRs in 30d
Description
Currently, I am working on research related to multi-objective optimization and using the mompo agent.
In the environment, some actions are discrete some are continuous.
How can I use mompo for this kind of hybrid action space?
Contributor guide
Assessment
This issue has not been assessed yet.