[KongchangAI]
Unverified50% confidenceFactExact time

PPO用于语言模型对齐时涉及四个需要同时维护的模型实例:策略模型(Actor)、冻结的SFT参考模型、奖励模型和评价模型(Critic)

1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/550662
API
curl https://kongchang.com/api/v1/knowledge/claims/550662
MCP
get_claim(id=550662)