Reinforcement learning toolbox multiple agents training

Since the RL toobox doesn't natively support MADDPG (currently), I tried to train multiple agents, each of which is working based on separate set of data from the same plant. I was wondering if it is possible to train multiple agents using the RL toolbox Simultaeaously based on different portions of data observed from the same plant?

Answer 1

[Emmanouil Tzorakoleftherakis]

As of R2020b release, Reinforcement Learning Toolbox lets you train multiple agents simultaneously in Simulink. Please see following examples for reference:

1. Train Multiple Agents for Path Following Control
2. Train Multiple Agents for Area Coverage
3. Train Multiple Agents to Perform Collaborative Task

Hope that helps

Answer 2

[Bhargavi Maganuru]

I understand you are looking for a way to simulate a multi-agent Reinforcement Learning environment. Unfortunately, the Reinforcement Learning Toolbox currently does not support multi-agent scenario. You would need to write your custom environment and training algorithms for such scenario.

Due to large amounts of request on this feature, the development team is actively working on the multi-agent feature now and it will be available in a future release. I have linked your email address to their release plan, and you shall receive a notification automatically once there is an update regarding the progress.

If you decide to write your own environment and training algorithm, the following documentation would be a good place to start:

https://www.mathworks.com/help/reinforcement-learning/matlab-environments.html

https://www.mathworks.com/help/reinforcement-learning/training-and-validation.html

[beni hadi]

please add my email to the release plan, too.

[Shabnam Noor]

Please link my email address to the release plan too. Thank you :)