Unverified50% confidenceFactExact time
Function approximation error can cause algorithms to become unstable or even diverge, and the risk is highest when function approximation, bootstrapping and off-policy learning occur simultaneously (the "deadly triad").
1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen prior knowledge about possible fault patterns is available, selecting a sparse penalty structure that matches them often yields significant performance gains over general-purpose algorithms76% similarUnverifieddeadly triad问题指函数逼近、自举更新和off-policy学习三者结合时产生的不稳定性73% similarUnverifiedPoint-wise sample selection strategies suffer from sensitivity and redundancy problems, which easily lead to overfitting of the acquisition function.72% similarUnverified级联失败是指单次工具调用错误会污染后续上下文，导致模型在错误的中间状态上继续推理，最终使整个任务偏轨72% similarUnverifiedIn agentic scenarios, watermarking may incur three hidden costs: decision-path drift, degraded format and structural reliability, and error accumulation across long chains.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1098725API
curl https://kongchang.com/api/v1/knowledge/claims/1098725MCP
get_claim(id=1098725)