Commit Graph

2 Commits (db2d948f9330e97caf44e5c8a60b76ff94682b69)

Author SHA1 Message Date
vanking 0b37f04f15
Update train_gated_grpo.py 2026-02-03 10:33:27 +08:00
vanking e84437a8ca
[add] Create train_gated_grpo.py
add gating term on grpo algorithm
2026-02-03 10:20:56 +08:00