Model techniques map
Techniquespost-trainingreinforcement learning algorithm

implementation detail · filed under post-training

Quality-Weighted Advantage Redistribution

Downweighting lower-quality passes and redistributing the removed positive advantage mass among passing trajectories.

Also called quality factors.

source
1
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

quality factors first downweight lower-quality passes, after which a common factor redistributes the removed positive advantage mass among passing trajectories.

usedpost trainingin MiMo-V2.6-Pro and MiMo-V2.6-FlashXiaomi

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.