Papers & Research

OpenAI proposes evolution strategies (ES) as a scalable alternative to reinforcement learning

Original title:Evolution strategies as a scalable alternative to reinforcement learning

AI summary

OpenAI found that evolution strategies (ES), a decades-old optimization technique, can match standard reinforcement learning methods on modern RL benchmarks such as Atari and MuJoCo while overcoming many of RL's inconveniences.

Key Takeaways

  • OpenAI found that evolution strategies (ES)
  • a decades-old optimization technique
  • can match standard reinforcement learning methods on modern RL benchmarks such as Atari and MuJoCo…

Quick Facts

Published
Updated
Source
OpenAI:官网动态(RSS · 排除企业/客户案例)
Category
Papers & Research
AI score
63
Read the original Read the full article at the original source
Why it matters

原文指出进化策略在 Atari/MuJoCo 基准上可媲美标准 RL,并克服 RL 的诸多不便,读者可借此了解另一种可扩展的优化路线。

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 proposes evolution strategies (ES) as a scalable alternative to reinforcement learning. March 24, 2017. https://new.nat6.net/en/news/bh7qfvh72r7xct59504ps6g1k/

View all →