implementation detail · filed under post-training
Continuous rollout with asynchronous reward computation and early termination
Combines continuous rollout, asynchronous reward computation, and early termination to reduce GPU idle time.
- 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.
Our design integrates continuous rollout, asynchronous reward computation, and early termination to minimize GPU idle time
usedsoftware implementationin MiMo-7B series RL training infrastructureXiaomi
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