Clear Filters
Clear Filters

Reinforcement Learning Agents generating zero episode

3 views (last 30 days)
Hello Matlab community,
I faced an issue for training a multiple agent problem in Matlab/Simulink. I tried to solve a very simple problem; however, training stops at episode 1.
Suppose that we have three discrete variables A=[1 2 3], B=[1 2 3], C=[1 2 3].
Reward function = A*B*C;
Observation= A+B+C;
I tried different parameters but it didn’t work. I attached the sample file for the reference. Very appreciate it if you can suggest potential solution to solve convergence issue.
Thanks for your time 😊

Accepted Answer

Ari Biswas
Ari Biswas on 4 Oct 2022
There is an issue with the way you specified the reset function. Your function resetRobots should return a Simulink.SimulationInput object, which is also an input argument to the function. So for e.g. the correct function signature should be:
function in = resetRobots(in, var1, var2, var3)
% write reset code
end
See this example to see how reset functions can be defined.
  1 Comment
Hamid Fazeli
Hamid Fazeli on 19 Oct 2022
Hi Ari,
Thank you so much for the suggestion. The problem was reset function. It was fixed :)

Sign in to comment.

More Answers (0)

Products


Release

R2021b

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!