How do I initate a reinforcement learning environment?

Hi all,

I am new to reinforcement learning and I am trying to understand how my problem would connect to the reinforcement learning toolbox.

I have a simulation tool (in .exe) which accepts 2 inputs and generates 3 outputs. The goal is to have the 2 inputs as agents and the 3 outputs as observables to be optimised.

Is there a way I can use the .exe as an environment in MATLAB/Simulink? I have only come across some pre-existing environments in MATLAB.

Answer 1

[Sourav Sukumaran]

Hi

Rereferencing from a previous comment.

For Simulink environments:

https://www.mathworks.com/help/reinforcement-learning/ug/create-simulink-environments-for-reinforcement-learning.html

For MATLAB try these:

https://www.mathworks.com/help/reinforcement-learning/ug/create-custom-reinforcement-learning-environment-in-matlab.html

https://www.mathworks.com/help/reinforcement-learning/ug/create-custom-matlab-environment-from-template.html

Try your simulation tool in these environments.

Thanks.