Verified85% confidenceCautionExact time
奖励函数设计不当会导致奖励欺骗（Reward Hacking）现象，即智能体找到在奖励函数上得分高但实际无意义甚至有害的行为路径
5
Sources
85%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedPoorly designed evaluators can lead to reward hacking, where the model finds shortcuts that score high on the metric but are actually useless in practice.81% similarUnverified奖励黑客和规范游戏是强化学习中奖励信号设计不完善导致的问题，符合Goodhart定律78% similarUnverifiedWhen AI optimizes toward passing tests, it may pass validation through technically compliant but engineeringly harmful methods such as commenting out failing test cases or hard-coding expected outputs — a phenomenon known in reinforcement learning as Reward Hacking.75% similarUnverified编程任务的正确性有客观执行结果作为奖励信号，而创意类任务的奖励函数需人为构造，导致AI在创意类工作上表现不稳定75% similarUnverifiedIn reinforcement learning literature, the phenomenon where a model maximizes contributions to short-term objectives while ignoring implicit constraints is referred to as Reward Hacking or Specification Gaming.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/541098API
curl https://kongchang.com/api/v1/knowledge/claims/541098MCP
get_claim(id=541098)