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.
Asynchronous reinforcement learningPartial rolloutAsynchronous RL frameworks for large-scale agent scaffolds and environment orchestrationToken-in-token-out (TITO)Asynchronous reinforcement learning infrastructureCo-located RL trainingData SchedulerDecoupled control plane and data planeDecoupling agent rollout into sandbox and worker containerDeficit-corrected schedulingLarge-scale asynchronous RL in synthesized tasksOne-step off-policy asynchronous reinforcement learningPredictive Rollout DispatchSample-grained garbage collectionSeamless Rollout EngineSLIMEToken-granularity persistence of rollout statesToken-level interruptionTool ManagerToolboxAdaptive Rollout ConcurrencyAdaptive Rollout SchedulingAgent LoopAgent-centric rollout execution