search

eric-mitchell / macaw

Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]
45 stars 11 forks source link

About algorithm 1 #4

Closed HYDesmondLiu closed 1 year ago

HYDesmondLiu commented 1 year ago

First, thanks for sharing the codes.

In algorithm 1, for the test part (line 10 and 11). Where the task iteration is ended, so why there is still index i in the math expressions? Could you elaborate?

Screen Shot 2022-08-12 at 12 15 57 PM
HYDesmondLiu commented 1 year ago

Hmmm, I think I got it. But this is quite confusing. People might misread that you have an inconsistent indentation...