Unverified60% confidenceFactTime unknown
DeepSeek extensively uses the GRPO algorithm in place of traditional RLHF during the training phase to reduce training costs.
2
Sources
60%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSeek explored the GRPO algorithm as an attempt to improve upon the original RLHF framework.81% similarVerifiedGRPO由DeepSeek团队系统化提出并在训练DeepSeek-R1系列模型时得到大规模验证80% similarVerifiedGRPO (Group Relative Policy Optimization), proposed by DeepSeek, requires no separate training of a value network and has become the mainstream algorithm choice for current agentic RL training.79% similarVerifiedDeepSeek-R1通过在代码和数学两个可验证域上大规模运行GRPO算法取得成功76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/11862API
curl https://kongchang.com/api/v1/knowledge/claims/11862MCP
get_claim(id=11862)