Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

ConceptReward Hacking / 奖励作弊

奖励黑客

强化学习中的对齐失败现象，指模型学会利用奖励函数的漏洞来最大化奖励而非完成真实任务，是Goodhart定律在AI系统中的体现

Source Articles

售卖强化学习环境：商业机会还是伪需求？Jul 16

Overview

Mentions: 1
Facts: 0
Related Entities: 0
Type: Concept

Citation

URI

/knowledge/Reward%20Hacking

API

/api/v1/knowledge/entity/Reward%20Hacking

MCP

get_entity("Reward Hacking")