OpenAI and DeepMind collaborate on learning from human preferences
Original title:Learning from human preferences
AI summary
OpenAI and the DeepMind safety team developed an algorithm that infers what humans want by having people judge which of two candidate behaviors is better. The work aims to eliminate hand-written objective functions and avoid simple proxies or goal misspecification for complex objectives that can lead to undesirable or dangerous behavior, as a step toward building safe AI systems.
Key Takeaways
- OpenAI and the DeepMind safety team developed an algorithm that infers what humans want by having…
- The work aims to eliminate hand-written objective functions and avoid simple proxies or goal…
- as a step toward building safe AI systems.
Quick Facts
- Published
- Updated
- Source
- OpenAI:官网动态(RSS · 排除企业/客户案例)
- Category
- Papers & Research
- AI score
- 70
原文说明该算法通过比较两种行为的优劣来推断人类偏好,从而免去人工编写目标函数,可作为对齐研究的背景参考。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenAI and DeepMind collaborate on learning from human preferences. June 13, 2017. https://new.nat6.net/en/news/vron7w516tsukjv0bfk7g7g24/