Asynchronous reinforcement learning
Technique · Training · 2 items since Apr 2026
Decoupling rollout generation from training updates so RL runs keep hardware busy.
Related
- Organizations
Trends
Items
- Oct 9
Xiaomi open-sources the MiMo-V2.6 RL stack
Xiaomi released the technical report and open-sourced the RL framework, environments, and training dynamics behind MiMo-V2.6, detailing asynchronous RL that consumes 2.7-3.7B tokens per step at up to 1M context with multi-layer defenses against reward hacking.
- Mar 31
Hugging Face's TRL v1.0
The post-training library reached a production-stable 1.0 covering 75+ methods, with asynchronous GRPO that offloads rollout generation to an external vLLM server to remove the synchronous generation bottleneck; it sees 3.3M PyPI downloads a month.