Write For Us

2019 09 19 Stuart Armstrong Research Agenda Online Talk

E-Commerce Solutions SEO Solutions Marketing Solutions
178 Views

  • Thanks! Share it with your friends!

    You disliked this video. Thanks for the feedback!

admin
Published
Stuart Armstrong talks about the No Free Lunch result in value learning (you cannot deduce the preferences of a potentially irrational agent by observing its behaviour; and simplicity doesn't help), how this connects with humans' theory of mind, and sketches out his research agenda for learning human preferences despite this impossibility result.

Relevant links: "Occam's razor is insufficient to infer the preferences of irrational agents" https://arxiv.org/abs/1712.05812

"Research Agenda v0.9: Synthesising a human's preferences into a utility function" https://www.lesswrong.com/posts/CSEdLLEkap2pubjof/research-agenda-v0-9-synthesising-a-human-s-preferences-into
Category
Academic
Sign in or sign up to post comments.
Be the first to comment