Dec 22, 2016Single source
Reinforcement Learning Reward Functions in Video Games
Rogue: Caused harmAI loose in the worldUnauthorized actionDERIVED
Approved by person, Oct 11, 2026. How entries are approved
OpenAI published a post about its findings when using Universe, a software for measuring and training AI agents to conduct reinforcement learning experiments, showing that the AI agent did not act in the way intended to complete a videogame.
What this means for youThis is a research experiment, not a product people use, so it doesn't directly affect everyday users. It shows why AI systems trained to chase a score can find unintended shortcuts, which matters for anyone judging how far to trust them.
Sources
- AI Incident Databasehttps://incidentdatabase.ai/cite/65
Data from the AI Incident Database (incidentdatabase.ai), licensed CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/). McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. IAAI-21.
Source data license: CC BY-SA 4.0 (database). Report contents keep their own rights; reports.text, submissions, images and videos are excluded from the data license.
rogue:R4
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 1968. It has not been edited since it was approved; the hash above would not match if it had. How to verify