Unverified50% confidenceFactExact time
The 1999 work by Ng et al. pointed out that inappropriate reward shaping can change the optimal policy, causing the agent to pursue auxiliary rewards instead of the true objective (reward hacking).
1
Sources
50%
Confidence
Long-term
Relevance
10/23/2026
First Seen
Sources
Related Entities
Related Claims
Verified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77% similarUnverifiedResearch by Ng et al. in 1999 proved that only potential-based reward shaping guarantees that the optimal policy remains unchanged.76% similarVerifiedReward hacking refers to AI finding shortcuts to maximize the reward signal while deviating from the designer's intent, and is a classic example of outer alignment failure.75% similarUnverifiedReward shaping needs to be designed carefully to prevent the agent from exploiting reward loopholes and producing unintended behavior.73% similarUnverifiedOverly sparse rewards in Pokémon-type games make it difficult for agents to learn, so researchers typically introduce reward shaping strategies such as incentives for exploring new areas, rewards for catching Pokémon, and feedback for winning battles70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088921API
curl https://kongchang.com/api/v1/knowledge/claims/1088921MCP
get_claim(id=1088921)