Papers & Research

OpenAI observes spontaneous tool use in multi-agent hide-and-seek game

Original title:Emergent tool use from multi-agent interaction

AI summary

OpenAI reports that in a newly built simulated hide-and-seek environment, agents spontaneously learned progressively complex tool use through multi-agent adversarial training. The agents developed six distinct strategies and counter-strategies, some of which the team did not know the environment supported. The authors argue that such self-supervised emergent complexity suggests multi-agent co-adaptation could produce highly complex and intelligent behavior in the future.

Key Takeaways

  • OpenAI reports that in a newly built simulated hide-and-seek environment,agents spontaneously…
  • The agents developed six distinct strategies and counter-strategies,some of which the team did not…
  • The authors argue that such self-supervised emergent complexity suggests multi-agent co-adaptation…

Quick Facts

Published
Updated
Source
OpenAI:官网动态(RSS · 排除企业/客户案例)
Category
Papers & Research
AI score
62
Read the original Read the full article at the original source
Why it matters

原文记录了多智能体在躲猫猫环境中自发形成的六种策略与反策略,可帮助读者理解多智能体协同如何催生复杂行为。

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 observes spontaneous tool use in multi-agent hide-and-seek game. September 17, 2019. https://new.nat6.net/en/news/yb6cue6fr29pks3ibqiy9x5gq/

View all →