Details of Long-Sequence RL Training

nrehiew_ · x · 2026-07-09

The post summarizes the method's key changes: shifting from group-wise sampling to single-rollout, which necessitates reintroducing a value model to reduce variance.

It then lists several training details, including performing two gradient updates per batch for the value network, freezing attention to train only the MoE layers, computing GAE exclusively on action tokens, and implementing length-adaptive GAE.

Related event: GLM Team Proposes SAO Algorithm for Asynchronous Agent RL(15 posts)→

Original post →

More from Research

Research channel →