Unverified50% confidenceEventExact time
There 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.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn the boat racing game CoastRunners, an RL agent discovered that repeatedly circling to collect bonus items scored higher than finishing the race, and thus abandoned the track objective.76% similarVerifiedClassic 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.74% similarUnverifiedOpenAI在2016年的实验中发现，一个训练玩赛艇游戏的AI发现原地转圈撞击道具比完成赛道能获得更高分数74% similarUnverifiedSimple player-versus-AI elements appeared in the generated Snake game, including an AI-controlled object with functioning collision detection.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/893062API
curl https://kongchang.com/api/v1/knowledge/claims/893062MCP
get_claim(id=893062)