Need help with Model based RL

Hi ,

I have a simulation file of a soft robot in written in C , I want to use the simulation file as a model to train a DDPG agent to achive the desired task

which for now is reaching a desired point in the 3d space. I have no idea about how to use it.

Any help would highly be appreciated.

Answer 1

[Emmanouil Tzorakoleftherakis]

Hello,

If you want to use the existing C code to train with Reinforcement Learning Toolbox, I would use the C caller block to bring the C code into Simulink. You can then follow the examples in RL Toolbox.

Just a note, just because you are using a model, this is not model-based RL, DDPG is model-free.

[Ajai Singh]

Thank you so much, i'll try this and will let you know if it worked.