Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Data re-sampling strategy

Resamples data for easy problems to improve rollout sampling efficiency and stabilize later-stage policy updates.

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 implement a data re-sampling strategy for easy problems to enhance rollout sampling efficiency and stabilize policy updates, particularly in the later phases of RL training.

useddata curationin MiMo-7B-RLXiaomi

Filed alongside

Other methods under post-training :: rollout & RL infrastructure.