general family · filed under post-training
Asynchronous reinforcement learning
An asynchronous reinforcement learning infrastructure decouples sample generation (rollout) from training in the RL post-training pipeline.1,2 It colocates rollout and training on the same devices, time-sharing their execution and maintaining high rollout concurrency to mitigate the long-tail bottleneck in the rollout phase.3,4
How this definition was written
Summarised by glm-5.3-flash from 2 sources; every sentence is checked against the quote it cites.
asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training
— GLM-5: from Vibe Coding to Agentic Engineeringfurther decouples generation from training to maximize GPU utilization
— GLM-5: from Vibe Coding to Agentic EngineeringWe colocate rollout and training on the same physical devices and time-share their execution
— DeepSeek V41 Tech Reportsignificantly mitigates the long-tail issue in the rollout phase by maintaining a sufficiently high level of concurrency
— DeepSeek V41 Tech Report
Also called asynchronous RL architecture, asynchronous training paradigm, asynchronous training, asynchronous RL framework, fully asynchronous training, fully asynchronous RL training pipeline.