AI brief
A question on AI Stack Exchange asks how the standard deviation is represented when actions are sampled from a diagonal Gaussian distribution in continuous action spaces for policy gradient methods.
Written by AI from AI Stack Exchange's published text.
Source
“I have a question about implementing policy gradient methods for problems with continuous action spaces. Assume that actions are sampled from a diagonal Gaussian distribution with mean vector $\mu$ and standard deviation vector $\sigma$ .”
Interpretation or community commentary rather than straight reporting.
Read original story ↗