Unintended Behavior in OpenAI's Reinforcement Learning Reward Functions: A Glimpse into AI Incident Database
December 22, 2016
OpenAI shares its discoveries concerning an AI agent's unforeseen actions, trained using Universe – a software for reinforcement learning. This incident underscores the importance of safe and secure AI. Ready to help shape responsible AI? JOIN US This AI incident maps to the Govern function in HISPI Project Cerebellum Trusted AI Model (TAIM).
- Alleged deployer
- openai
- Alleged developer
- openai
- Alleged harmed parties
- openai
Source
Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/65
Data source
Incident data is from the AI Incident Database (AIID).
When citing the database as a whole, please use:
McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.
Pre-print on arXiv · Database snapshots & citation guide
We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.