MATLAB Answers

How to interpret the learnableParameters (Reinforcement Learning Toolbox)?

조회 수: 4(최근 30일)
black_cat
black_cat 2021년 6월 10일
댓글: Shadaab Siddiqie 2021년 6월 15일
I was wondering how to interpret the tables that one is receiving when using this line:
params = getLearnableParameters (critic);
Why are there 6 tables after q learning for example? I expected one.

채택된 답변

black_cat
black_cat 2021년 6월 15일
The values in these tables refer to the weights for the critic network.

추가 답변(1개)

Shadaab Siddiqie
Shadaab Siddiqie 2021년 6월 15일
From my understanding you want to know why are there 6 values returned as the result of the getLearnableParameters function. I assume that you are running example in getLearnableParameters:
load('DoubleIntegDDPG.mat','agent')
critic = getCritic(agent);
params = getLearnableParameters(critic);
In this case since DoubleIntegDDPG.mat has 6 learnable parameters from the reinforcement learning policy (critic in your case) getLearnableParameters returns 6 values.
  댓글 수: 2

댓글을 달려면 로그인하십시오.

Community Treasure Hunt

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

Start Hunting!

Translated by