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

À propos de cet épisode

<p>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.</p> <p>EPISODE LINKS:<br /> Hutter Prize: <a href="http://prize.hutter1.net">http://prize.hutter1.net</a><br /> Marcus web: <a href="http://www.hutter1.net">http://www.hutter1.net</a><br /> Books mentioned:<br /> &#8211; Universal AI: <a href="https://amzn.to/2waIAuw">https://amzn.to/2waIAuw</a><br /> &#8211; AI: A Modern Approach: <a href="https://amzn.to/3camxnY">https://amzn.to/3camxnY</a><br /> &#8211; Reinforcement Learning: <a href="https://amzn.to/2PoANj9">https://amzn.to/2PoANj9</a><br /> &#8211; Theory of Knowledge: <a href="https://amzn.to/3a6Vp7x">https://amzn.to/3a6Vp7x</a></p> <p><span style="font-weight: 400;">This conversation is part of the Artificial Intelligence podcast.</span>&#160;If you would like to get more information about this podcast go to <a href="https://lexfridman.com/ai">https://lexfridman.com/ai</a> or connect with @lexfridman on <a href="https://twitter.com/lexfridman">Twitter</a>, <a href="https://www.linkedin.com/in/lexfridman/">LinkedIn</a>, <a href="https://www.facebook.com/lexfridman">Facebook</a>, <a href="https://medium.com/@lexfridman">Medium</a>, or <a href="https://www.youtube.com/lexfridman">YouTube</a> where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on <a href="https://podcasts.apple.com/us/podcast/artificial-intelligence/id1434243584">Apple Podcasts</a>, follow on <a href="https://open.spotify.com/show/2MAi0BvDc6GTFvKFPXnkCL">Spotify</a>, or support it on <a href="https://www.patreon.com/lexfridman">Patreon</a>.</p> <p>This episode is presented by Cash App. Download it (<a href="https://apps.apple.com/us/app/cash-app/id711923939">App Store</a>, <a href="https://play.google.com/store/apps/details?id=com.squareup.cash&#38;hl=en_US">Google Play</a>), use code &#8220;LexPodcast&#8221;.&#160;</p> <p>Here&#8217;s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.</p> <p>OUTLINE:<br /> 00:00 &#8211; Introduction<br /> 03:32 &#8211; Universe as a computer<br /> 05:48 &#8211; Occam&#8217;s razor<br /> 09:26 &#8211; Solomonoff induction<br /> 15:05 &#8211; Kolmogorov complexity<br /> 20:06 &#8211; Cellular automata<br /> 26:03 &#8211; What is intelligence?<br /> 35:26 &#8211; AIXI &#8211; Universal Artificial Intelligence<br /> 1:05:24 &#8211; Where do rewards come from?<br /> 1:12:14 &#8211; Reward function for human existence<br /> 1:13:32 &#8211; Bounded rationality<br /> 1:16:07 &#8211; Approximation in AIXI<br /> 1:18:01 &#8211; Godel machines<br /> 1:21:51 &#8211; Consciousness<br /> 1:27:15 &#8211; AGI community<br /> 1:32:36 &#8211; Book recommendations<br /> 1:36:07 &#8211; Two moments to relive (past and future)</p>