Reinforcement Learning Agents generating zero episode
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
Hamid Fazeli
el 1 de Oct. de 2022
Comentada: Hamid Fazeli
el 19 de Oct. de 2022
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 😊
0 comentarios
Respuesta aceptada
Ari Biswas
el 4 de Oct. de 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.
Más respuestas (0)
Ver también
Categorías
Más información sobre Training and Simulation en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!