Model techniques map
Techniquespost-trainingreinforcement learning algorithm

general family · filed under post-training

Penalty Module

A configurable module that applies loss masking and advantage shaping.

source
1
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

a configurable Penalty Module applies loss masking and advantage shaping

coreunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

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