Papers & Research

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
Read the original Read the full article at the original source
Why it matters

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.

Original article · AIHOT entry

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/

View all →