#75 – Marcus Hutter: Universal Artificial Intelligence, AIXI, and AGI

46 snips

Feb 26, 2020

Marcus Hutter, a senior research scientist at DeepMind and professor at Australian National University, dives deep into the world of artificial general intelligence. He discusses the innovative AIXI model and how it approaches intelligence through concepts like Kolmogorov complexity and reinforcement learning. The conversation explores the significance of simplicity in theories, the challenges of defining AI, and the philosophical implications of Gödel machines and consciousness. Hutter emphasizes the interplay between exploration and decision-making, shedding light on the future of AI.

Ask episode

AI Snips

Chapters

Books

Transcript

Episode notes

INSIGHT

Kolmogorov Complexity

Kolmogorov complexity measures the shortest program that can reproduce a given data set.
While the universe might have low Kolmogorov complexity, subsets of it, like Earth, can be highly complex.

ANECDOTE

Library of All Books

A library containing all possible books has low information content, despite its vastness.
Subsets of this library, like a typical library with selected books, can be information-rich.

INSIGHT

Defining Intelligence

Intelligence measures an agent's ability to perform well in diverse environments.
Traits like creativity, memorization, planning, and knowledge emerge from this ability.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Marcus Hutter is a senior research scientist at DeepMind and professor at Australian National University. Throughout his career of research, including with Jürgen Schmidhuber and Shane Legg, he has proposed a lot of interesting ideas in and around the field of artificial general intelligence, including the development of the AIXI model which is a mathematical approach to AGI that incorporates ideas of Kolmogorov complexity, Solomonoff induction, and reinforcement learning.

EPISODE LINKS:
Hutter Prize: http://prize.hutter1.net
Marcus web: http://www.hutter1.net
Books mentioned:
– Universal AI: https://amzn.to/2waIAuw
– AI: A Modern Approach: https://amzn.to/3camxnY
– Reinforcement Learning: https://amzn.to/2PoANj9
– Theory of Knowledge: https://amzn.to/3a6Vp7x

This conversation is part of the Artificial Intelligence podcast. If you would like to get more information about this podcast go to https://lexfridman.com/ai or connect with @lexfridman on Twitter, LinkedIn, Facebook, Medium, or YouTube where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on Apple Podcasts, follow on Spotify, or support it on Patreon.

This episode is presented by Cash App. Download it (App Store, Google Play), use code “LexPodcast”.

Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.

OUTLINE:
00:00 – Introduction
03:32 – Universe as a computer
05:48 – Occam’s razor
09:26 – Solomonoff induction
15:05 – Kolmogorov complexity
20:06 – Cellular automata
26:03 – What is intelligence?
35:26 – AIXI – Universal Artificial Intelligence
1:05:24 – Where do rewards come from?
1:12:14 – Reward function for human existence
1:13:32 – Bounded rationality
1:16:07 – Approximation in AIXI
1:18:01 – Godel machines
1:21:51 – Consciousness
1:27:15 – AGI community
1:32:36 – Book recommendations
1:36:07 – Two moments to relive (past and future)