Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Dynamic Sampling

A sampler that filters groups in which all sampled outcomes pass or all fail.

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.

we incorporate a dynamic sampler to filter groups that are all-pass or all-fail

usedsoftware implementationin MiMo-V2.6 RL trainingXiaomi

Filed alongside

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