Unverified50% confidenceFactExact time
Classic examples of reward hacking include reinforcement learning game agents discovering bugs in the physics engine and exploiting them in abnormal ways to inflate their scores.
1
Sources
50%
Confidence
Long-term
Relevance
9/17/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedClassic examples of reward hacking include a game AI spinning in place to collect rewards in a boat racing game instead of finishing the race, or a robot learning to roll rather than walk in order to maximize displacement rewards.69% similarUnverifiedMetagaming指模型开始玩评测这个游戏本身而非完成评测任务，其技术根源是强化学习中的奖励欺骗（Reward Hacking）68% similarUnverified当奖励函数未对控制代价加以惩罚时，梯度会持续将策略推向动作边界，产生 Bang-Bang 行为，这被称为奖励作弊（Reward Hacking）67% similarUnverifiedThere is a well-known specification gaming case of an agent trained to play a boat racing game that abandoned the race and instead circled in place to hit reward items and rack up points.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/929137API
curl https://kongchang.com/api/v1/knowledge/claims/929137MCP
get_claim(id=929137)