Implementing the new P4O algorithm in cleanRL #474
AndikanAffiah
started this conversation in
Ideas
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.
-
I would love to see the P4O being implemented in cleanRL
The paper authors claim a 2.9× increase in
performance with the inclusion of predictive processing, while requiring 22% fewer parameters.
reference: https://arxiv.org/abs/2211.06236
And a possible combination with the new xLSTM that has improved performance compared to prevous implementations of LSTM
reference: https://arxiv.org/pdf/2405.04517
@vwxyzjn
Beta Was this translation helpful? Give feedback.
All reactions