Unverified50% confidenceFactExact time
Q-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
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedQ-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78% similarUnverifiedOff-policy algorithms (such as SAC and DQN) can be trained on data collected by any policy, are capable of maintaining a replay buffer of millions of experiences for repeated learning, and have higher sample efficiency than on-policy methods.64% similarVerified量化感知训练（QAT）在训练过程中模拟量化误差反向传播，效果通常优于训练后量化（PTQ）61% 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% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/805330API
curl https://kongchang.com/api/v1/knowledge/claims/805330MCP
get_claim(id=805330)