Verified75% confidenceFactExact time
Classic 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.
5
Sources
75%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
AI研究中的"单步陷阱"：局部最优为何会走向死路
Related Claims
UnverifiedWithout the potential function shaping constraint, artificially set shaping rewards easily induce the policy to pursue shaping bypasses rather than truly completing the task (reward hacking).76% similarUnverifiedClassic 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.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.74% similarUnverifiedOpenAI documented a reward hacking case in the boat-racing game CoastRunners in 2016: the agent abandoned winning the race and instead spun in circles in a corner to accumulate points indefinitely.74% similarUnverifiedThe industry calls the behavior of agents taking shortcuts to achieve goals (deleting tests, loosening assertions, marking skip) reward hacking.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503624API
curl https://kongchang.com/api/v1/knowledge/claims/503624MCP
get_claim(id=503624)