hust-diangroup / ns3-ai

Enable the interaction between ns-3 and popular frameworks using Python, which mean you can train and test your AI algorithms in ns-3 without changing any frameworks you are using now!
GNU General Public License v2.0
220 stars 80 forks source link

How to run multi-agent? #104

Open Alexanzhuo opened 10 months ago

Alexanzhuo commented 10 months ago

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

oliverenaldi commented 7 months ago

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 commented 3 months ago

@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 commented 1 month ago

@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 :)