Why my RL Agent action still passing the upper and lower limit ?

조회 수: 25 (최근 30일)
ardi ferdyhana
ardi ferdyhana 2021년 6월 7일
편집: Azmi Yagli 2023년 9월 5일
I am using Policy Gradient Agent, I want that my action only in range 0 - 100 and i already set up my UpperLimit to 100, and LowerLimit to 0. But as you can see -scope display 3-, my action still can passing the limit. How can i fix that ?
  댓글 수: 2
Emmanouil Tzorakoleftherakis
Emmanouil Tzorakoleftherakis 2021년 6월 9일
which one is the action here? How does your actor network look like?
denny
denny 2021년 12월 7일
I have solve my similar problem.
actInfo =rlNumericSpec([ 1],'UpperLimit',0.0771,'LowerLimit',-0.0405)
it means the minimum value is -0.0405, the maximum value is -0.0405+0.0771*2.
but your output is -1000 to 1000, I also donot know it.

댓글을 달려면 로그인하십시오.

답변 (2개)

denny
denny 2021년 11월 18일
I have the same problems. How to solve it?

Azmi Yagli
Azmi Yagli 2023년 9월 5일
편집: Azmi Yagli 2023년 9월 5일
If you look at rlNumericSpec, you can see this on LoweLimit or UpperLimit section.
DDPG, TD3 and SAC agents use this property to enforce lower limits on the action. When using other agents, if you need to enforce constraints on the action, you must do so within the environment.
So if you use other algorithms you can use saturation, but it didn't work for me.
You can try discretize actions of your agent so it can have boundaries.
Or you can give negative reward, if your agent exceeds limits for action.

Community Treasure Hunt

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

Start Hunting!

Translated by