[QUESTION] Missing Σ (sigma) symbol in Unit 4 "Gradient Ascent and the Policy-gradient Theorem"

huggingface / deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.

Apache License 2.0

3.71k stars 564 forks source link

[QUESTION] Missing Σ (sigma) symbol in Unit 4 "Gradient Ascent and the Policy-gradient Theorem" #527

Open pgiouroukis opened 1 month ago

pgiouroukis commented 1 month ago

I am referring to this section and specifically to this image:

Shouldn't there be a Σ (sigma) symbol right before the gradient operator? For reference, here is how the Policy-gradient Theorem is derived in OpenAI's "Spinning Up" course.