Open Models Almanac
Methodspost-trainingpolicy distillation

single mention · post-training

Behavior–Proximal Policy Decoupling

An implementation detail that separates the behavior policy from the proximal policy to stabilize asynchronous MOPD.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See policy distillation for the methods filed beside it.

Filed under post-training › policy distillation