How can I have several actions for a DQN in the Reinforcement Learning Toolbox?

6 vues (au cours des 30 derniers jours)
I'm trying to define the output of a DQN agent with a custom environment, and can't use the actionInfo = rlFiniteSetSpec() correctly.
I'm trying to control 3 actuators that will receive commands 0 and 1.
I always get number of actions = 1.
And the documentation is not clear as it's a new toolbox.
Any suggestions?
  3 commentaires
Rusczak
Rusczak le 8 Juil 2020
Yes,
I followed Emmanouil's suggestion:
actInfo = rlFiniteSetSpec({[0; 0; 0]; [1; 1; 1]; ...
[1; 0; 0]; [0; 1; 0]; [0; 0; 1]; ...
[1; 1; 0]; [0; 1; 1]; [1; 0; 1]})
Huzaifah Shamim
Huzaifah Shamim le 9 Juil 2020
Oh nice okok. What custom environment where you trying to make?
Also how should I approach it if i have 3 agents (like your three actuators) but 12 actions could be applied to them?

Connectez-vous pour commenter.

Réponse acceptée

Emmanouil Tzorakoleftherakis
If you type
help rlFiniteSetSpec
the second example is
spec = rlFiniteSetSpec({[0,1];[1,1];[1,2];[1,3]})
If you define all possible combinations of the discrete inputs in a cell array as above, that should work (think of a single action as one possible combination of your 3 actuator commands).
I hope this helps.

Plus de réponses (0)

Community Treasure Hunt

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

Start Hunting!

Translated by