How to run multi-agent?

[Alexanzhuo]

Dear developer:
How can I run a multi-agent instance? It is present in NS3 Gym, but not in NS3 AI.

[oliverenaldi]

Has any of the developers taken a look about this issue? Is it possible to derive a new env class from the Ns3AiEnv gym environment?

[OliverZim]

@Alexanzhuo @oliverenaldi

Hey,
I am currently part of a project that builds upon ns3-ai to create a framework for realistic multi-agent RL in ns3. May I ask what you intend to use multi-agent rl for in ns3? We would appreciate getting some feedback from users.
You can send me an email to oliver.zimmermann@student.hpi.de in case you would like to connect.

[OliverZim]

@Alexanzhuo @oliverenaldi
Are you still interested in this use-case? We have opened a pull-request #126 regarding this topic that supports multi-agent envs. Maybe you can take a look at it and give some feedback.

Any interaction would be appreciated.
Thanks a lot :)