How GAE calculates in Reinforement Learning Toolbox(PPO)?

2 views (last 30 days)
TigerSee
TigerSee on 14 Feb 2021
Answered: Emmanouil Tzorakoleftherakis on 16 Feb 2021
A difference between help center and reference[3] about TD error.
Why in Generalized Advantage Estimator?
https://ww2.mathworks.cn/help/reinforcement-learning/ug/ppo-agents.html

Sign in to answer this question.

Accepted Answer

Emmanouil Tzorakoleftherakis
Hello,
Thank you for catching this typo - it should be Gt = Dt+V. I have let the documentation team know.

More Answers (0)

Categories

Find more on Financial Toolbox in Help Center and File Exchange

Tags

Products


Release

R2020a

Community Treasure Hunt

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

Start Hunting!