question about external action of DDPG

3 Ansichten (letzte 30 Tage)
Zicheng
Zicheng am 7 Sep. 2023
Beantwortet: Emmanouil Tzorakoleftherakis am 25 Sep. 2023
Is anyone know the loss function of the Q-network when I set external action=1 during training process?(DDPG)

Melden Sie sich an, um diese Frage zu beantworten.

Akzeptierte Antwort

Emmanouil Tzorakoleftherakis
The loss function does not change. What happens is that the experience buffer is populated with the action from the external signal and the respective observations/reward.

Weitere Antworten (0)

Kategorien

Mehr zu Deep Learning Toolbox finden Sie in Help Center und File Exchange

Tags

Produkte


Version

R2021b

Community Treasure Hunt

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

Start Hunting!

Translated by