Model techniques map
Techniquespost-trainingrollout & RL infrastructure

general family · filed under post-training

Asynchronous reinforcement learning infrastructure

Infrastructure for asynchronous RL; the evidence identifies SLIME as one instance but does not specify a single distinguishing mechanism for this broader label.

Also called asynchronous RL infrastructure.

sources
2
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

we developed slime, a novel asynchronous RL infrastructure that substantially improves training throughput and efficiency, enabling more fine-grained post-training iterations.

usedoptimizationin GLM-5Z.ai

we have engineered a new asynchronous reinforcement learning infrastructure.

usedsoftware implementationin GLM-5Z.ai

Filed alongside

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