Skip to content
This repository has been archived by the owner on Dec 11, 2022. It is now read-only.

Are multi-agent environments supported? #155

Open
bbalaji-ucsd opened this issue Dec 12, 2018 · 1 comment
Open

Are multi-agent environments supported? #155

bbalaji-ucsd opened this issue Dec 12, 2018 · 1 comment
Labels
enhancement help wanted priority/p3 enhancements not currently in focus or low impact bugs
Projects
Coach Dev

Comments

@bbalaji-ucsd
Copy link

This comment in code indicates that they are supported:
https://github.com/NervanaSystems/coach/blob/master/rl_coach/level_manager.py#L50

But don't see any documentation or examples.
@gal-leibovich
Copy link
Contributor

Hi @bbalaji-ucsd,

You are correct, there is infrastructure in place to enable future support in multi-agent RL, but currently it is not officially supported. This is why there are no examples nor documentation. Adding support will probably require a new multi-agent based GraphManager, and potential changes to LevelManager.
@scttl scttl added this to To do in Coach Dev Jan 10, 2019
@galnov galnov moved this from To do to P3 in Coach Dev Jan 14, 2019
@balajismaniam balajismaniam added the priority/p3 enhancements not currently in focus or low impact bugs label Jan 16, 2019
@balajismaniam balajismaniam moved this from P3 to Groomed but Not Started in Coach Dev Jan 16, 2019
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
enhancement help wanted priority/p3 enhancements not currently in focus or low impact bugs
3 participants
@bbalaji-ucsd @balajismaniam @gal-leibovich