Unverified50% confidenceFactExact time
GRPO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
1
Sources
50%
Confidence
Long-term
Relevance
7/10/2026
First Seen
Sources
AI智能体强化学习：RLHF与Agentic RL核心技术解析
rss7/1/2026
Related Claims
VerifiedDeepSeek-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80% similarUnverifiedDeepSeek在训练阶段大量使用GRPO算法替代传统的RLHF来压缩训练成本80% similarVerifiedGRPO（Group Relative Policy Optimization）由DeepSeek提出，无需单独训练价值网络，已成为当前智能体RL训练的主流算法选择80% similarUnverifiedDeepSeek探索了GRPO算法，作为对RLHF原始框架的改进尝试79% similarUnverifiedDeepSeek团队报告，仅用GRPO在数学和代码数据上进行强化学习而不经过监督微调，模型便自发出现反思、回溯验证等链式推理行为（aha moment）77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/461042API
curl https://kongchang.com/api/v1/knowledge/claims/461042MCP
get_claim(id=461042)