search

LucasAlegre / morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.
https://lucasalegre.github.io/morl-baselines
MIT License
295 stars 47 forks source link

[PGMORL] remaining iterations bugfix #25

Closed mathieu-reymond closed 1 year ago

mathieu-reymond commented 1 year ago

I think I found a bug in the training iterations, since self.iteration starts at self.warmup_iterations after the warmup phase, it should be taken into account.

ffelten commented 1 year ago

I checked out the code on my machine and the tests are passing. Very weird that the gh runner gets stuck...

EDIT: I seem to have found the culprit. @mathieu-reymond can you merge the main branch into yours and try again?

mathieu-reymond commented 1 year ago

@ffelten voila, hope everything is in order now