Naive implementation of rollout logp correction in RL training (#179)
* naive implement of rollout logp corection * clean code
C
Chengxing Xie committed
067d65a4a4bcb3074f0e10085ca6b32cc213c19b
Parent: e61b2d2
Committed by GitHub <noreply@github.com>
on 8/26/2025, 3:00:14 AM