web.archive.org/web/20230604210036/https:/ai.stanford.edu/blog/reward-isnt-free

Preview meta tags from the web.archive.org website.

Linked Hostnames

1

Thumbnail

Search Engine Appearance

Google

https://web.archive.org/web/20230604210036/https:/ai.stanford.edu/blog/reward-isnt-free

Reward Isn’t Free: Supervising Robot Learning with Language and Video from the Web

This work was conducted as part of SAIL and CRFM.



Bing

Reward Isn’t Free: Supervising Robot Learning with Language and Video from the Web

https://web.archive.org/web/20230604210036/https:/ai.stanford.edu/blog/reward-isnt-free

This work was conducted as part of SAIL and CRFM.



DuckDuckGo

https://web.archive.org/web/20230604210036/https:/ai.stanford.edu/blog/reward-isnt-free

Reward Isn’t Free: Supervising Robot Learning with Language and Video from the Web

This work was conducted as part of SAIL and CRFM.

  • General Meta Tags

    11
    • title
      Reward Isn’t Free: Supervising Robot Learning with Language and Video from the Web | SAIL Blog
    • title
      Reward Isn't Free: Supervising Robot Learning with Language and Video from the Web | The Stanford AI Lab Blog
    • charset
      utf-8
    • viewport
      width=device-width, initial-scale=1, maximum-scale=1
    • generator
      Jekyll v3.9.0

  • Open Graph Meta Tags

    6
    • og:title
      Reward Isn’t Free: Supervising Robot Learning with Language and Video from the Web
    • US country flagog:locale
      en_US
    • og:description
      This work was conducted as part of SAIL and CRFM.
    • og:url
      https://web.archive.org/web/20230530143330/http://ai.stanford.edu/blog/reward-isnt-free/
    • og:site_name
      SAIL Blog

  • Twitter Meta Tags

    6
    • twitter:card
      summary
    • twitter:title
      Reward Isn't Free: Supervising Robot Learning with Language and Video from the Web
    • twitter:description
      Where do the rewards for robotic reinforcement learning come from? In this blog post we study how using crowdsourced language annotations and videos of humans, we can learn reward functions in a scalable way and enable them to generalize more broadly.
    • twitter:creator
      @StanfordAILab
    • twitter:card
      summary_large_image

  • Link Tags

    15
    • alternate
      https://web.archive.org/web/20230530143330/http://ai.stanford.edu/blog/feed.xml
    • canonical
      https://web.archive.org/web/20230530143330/http://ai.stanford.edu/blog/reward-isnt-free/
    • canonical
      https://web.archive.org/web/20230530143330/http://ai.stanford.edu/blog/reward-isnt-free/
    • icon
      /web/20230530143330im_/https://ai.stanford.edu/blog/assets/img/favicon-32x32.png
    • icon
      /web/20230530143330im_/https://ai.stanford.edu/blog/assets/img/favicon-16x16.png

Links

30