How to set a variable learning rate in Reinforcement Learning Toolbox?

1 view (last 30 days)

Christian Bianchi on 2 Oct 2023

0
Link

Direct link to this question

https://ch.mathworks.com/matlabcentral/answers/2028094-how-to-set-a-variable-learning-rate-in-reinforcement-learning-toolbox

Answered: Emmanouil Tzorakoleftherakis on 2 Oct 2023

Accepted Answer: Emmanouil Tzorakoleftherakis

In Reinforcement Learning Toolbox, when setting the actor and critic options with "rlOptimizerOptions" for a PPO agent, is there a way to set a variable learning rate (e.g. decreasing with time) instead of a constant value?

Thanks!

0 Comments
Show -2 older commentsHide -2 older comments

Accepted Answer

Emmanouil Tzorakoleftherakis on 2 Oct 2023

0
Link

Direct link to this answer

https://ch.mathworks.com/matlabcentral/answers/2028094-how-to-set-a-variable-learning-rate-in-reinforcement-learning-toolbox#answer_1323549

Hi,

This is not supported as of R2023b but the developmet team is aware and will look into supporting this capability in the future.

0 Comments
Show -2 older commentsHide -2 older comments

Products

Reinforcement Learning Toolbox

Release

R2023a

Community Treasure Hunt

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

Start Hunting!