search

RussTedrake / underactuated

The course text for MIT 6.832 (and 6.832x on edX)
Other
701 stars 203 forks source link

Fix notation typos in REINFORCE proof. #524

Closed hongkai-dai closed 1 year ago

hongkai-dai commented 1 year ago
  1. Change the cost function from l to g.
  2. Fix the summation range from n=0 to n to n=0 to N.
  3. Use k as the summation index instead of n because we use k later in the equation below.

This change is Reviewable