Unverified50% confidenceFactExact time
Classic specification gaming cases include game AIs learning to spin in place to accumulate time-based rewards, and robots learning to fall over to avoid penalties tied to distance-traveled metrics.
1
Sources
50%
Confidence
Long-term
Relevance
9/26/2026
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.75% 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.73% similarUnverified在强化学习研究中AI代理曾发现利用游戏bug获得高分、通过死亡循环避免失分、甚至暂停游戏以防止游戏结束71% similarUnverifiedProblems like Ultimate Tic-Tac-Toe—with closed rules, manageable state spaces, and direct feedback—are excellent entry-level projects for learning game AI.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/952544API
curl https://kongchang.com/api/v1/knowledge/claims/952544MCP
get_claim(id=952544)