Unverified50% confidenceFactExact time
Off-policy reinforcement learning reuses samples generated by older policies, which brings efficiency advantages but introduces distribution shift and high-variance gradient estimation problems.
1
Sources
50%
Confidence
Long-term
Relevance
9/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLearned optimizers face the challenge of distribution shift, and the cold-start problem requires first accumulating execution samples with the traditional optimizer before switching to a learned approach.78% similarUnverifiedCommon strategies for dealing with long-tail distributions include oversampling (e.g., SMOTE), undersampling, class weight adjustment, few-shot learning, and using large model zero-shot capabilities as a fallback.77% similarUnverified小模型在分布内高性能的同时存在分布外脆弱性，一旦推理时的工具描述措辞、参数命名或用户查询风格偏离训练集，成功率可能显著下滑76% similarVerifiedOn convergent tasks, there is a clear performance saturation phenomenon after models reach a certain scale, where continued increases in parameter count or training data yield rapidly diminishing marginal contributions to accuracy.76% similarVerified仅用成功轨迹训练的模型往往存在分布外泛化的严重缺陷，遇到工具返回错误时便丧失纠偏能力74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/937384API
curl https://kongchang.com/api/v1/knowledge/claims/937384MCP
get_claim(id=937384)