Unverified50% confidenceFactExact time
Q-Learning 与 SARSA 的核心区别在于更新目标中是取 max（Q-Learning）还是取实际执行的动作值（SARSA），SARSA 在悬崖行走等环境中会学习到更保守但更安全的策略
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQ-Learning 是 off-policy 的 TD 控制方法，直接学习最优动作价值函数；SARSA 是 on-policy 方法，更新时使用智能体实际选择的下一个动作78% similarUnverifiedThe difference between SaaStr.ai and general-purpose large language models lies in its being specifically trained on curated B2B wisdom and expert insights.57% similarUnverifiedQK Normalization (applying LayerNorm separately to the Query and Key in Attention) has been proven to significantly improve training stability for ultra-large-scale models and has been adopted by models such as Gemma 2.57% similarUnverifiedMamba-2通过将选择性SSM重新表述为结构化状态空间对偶（SSD）框架，揭示了SSM与注意力机制的深层联系，使训练速度提升2-8倍53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/805331API
curl https://kongchang.com/api/v1/knowledge/claims/805331MCP
get_claim(id=805331)