NeMo-RL Support for Policy gradients #440
KalyanChakravarthyK
started this conversation in
Model Discussion
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Does NeMo-RL support heterogeneous policy gradients (mixing PPO with Q-learning) in multi-agent settings? If so, how are gradient conflicts or non-stationarity managed?"
Beta Was this translation helpful? Give feedback.
All reactions