Model techniques map
Techniquespost-trainingrollout & RL infrastructure

specific method · filed under post-training

Bounding the maximum off-policy ratio

Controls sample dispatch and training-sample waiting to bound how far asynchronous training data can deviate from the current model.

Also called bound the maximum off-policy ratio.

source
1
model
1
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.

by tuning the logic that controls sample dispatching and the waiting condition for training samples, we can bound the maximum off-policy ratio, ensuring that the training data does not deviate excessively from the current model

usedpost trainingin DeepSeek-V4.1DeepSeek

Filed alongside

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