Dynamically change a block input during Deep Reinforcement Learning after each episode. How To?
Show older comments
I have a constant block that takes a single input from the base MATLAB workspace. How do I set up my enviroment such that it accepts one of seven available inputs (at random or in a cycle)? This input should change between episodes.
Thank you.
1 Comment
Abdul Basith Ashraf
on 6 Oct 2020
Edited: Abdul Basith Ashraf
on 6 Oct 2020
Answers (1)
Emmanouil Tzorakoleftherakis
on 12 Oct 2020
0 votes
Hello,
Please have a look at this example, and in particular the 'localResetFcn' at the bottom ('setBlockParameter'in the reset function is one option).
Categories
Find more on Reinforcement Learning in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!