Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Advantage Shaping

A penalty-module operation that sets, scales, or subtracts advantages on flagged tokens.

Also called Advantage shaping on flagged tokens.

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.

advantage shaping sets, scales, or subtracts the advantages on hit tokens

usedunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

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