MuZero: DeepMind’s New AI Mastered More Than 50 Games

📝 The paper "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" is available here:

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Benji Rabhan, Brian Gilman, Bryan Learn, Christian Ahlin, Claudio Fernandes, Daniel Hasegan, Dan Kennedy, Dennis Abts, Eric Haddad, Eric Martel, Evan Breznyik, Geronimo Moralez, James Watt, Javier Bustamante, John De Witt, Kaiesh Vohra, Kasia Hayden, Kjartan Olason, Levente Szabo, Lorin Atzberger, Lukas Biewald, Marcin Dukaczewski, Marten Rauschenberg, Maurits van Mastrigt, Michael Albrecht, Michael Jensen, Nader Shakerin, Owen Campbell-Moore, Owen Skarpness, Raul Araújo da Silva, Rob Rowe, Robin Graham, Ryan Monsurate, Shawn Azman, Steef, Steve Messina, Sunil Kim, Taras Bobrovytsky, Thomas Krcmar, Torsten Reil, Tybie Fitzhugh.

Károly Zsolnai-Fehér's links:

[FuZZbaLLbee]

Generalization is also very important for use of RL outside of gaming

[PerfectlyNormalBeast]

15 years from now: This general ai can make a near perfectly performing narrow ai for any game it sees

[ctbur]

4:31 Did this guy just laugh at a cloud console?

[LegoEddy]

You might want to have a look at the paper "Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning" from Google Brain. They aim to have a (bird-) classifier that can detect objects (bird species) it has never seen before solely by a semantic description.

[EctoMorpheus]

What happened to actually explaining how the algorithm works? Still, thanks for the video! I'll look it up myself

[TheDemolition]

Always love the content from you. Is it possible to go over "why" certain AI are outperforming others in a given area? When possible of course.

I think that would add a much needed element for those of us that find this fascinating. Currently working through a math major and it would add some more depth for like minded individuals who don't necessarily have time to read through the papers.

Just a thought. Appreciate your channel!

[MrKarlyboy]

Confirms again the home of AI is the UK that's pioneered this via Turin's vision and the Deep Mind team started and built in the UK. So much is going on this incredible Island.

[GodOfReality]

I really wish my dream of seeing something like AlphaZero play an old MS-DOS game from 1995 called Descent would come true. That would be something absolutely fascinating to observe, how would optimal play look in a game like that, especially to see things like teams or some of the other alternate game modes.

[peterwilkinson]

are there videos of it playing any of these games? I would love to watch it play :D

[emilemil]

I feel that what made the Dota AI more interesting than examples like this, was that it was shown to beat humans when playing under the same conditions as us. That didn't just involve having the same limited information, but also things like slowing down the AI's reaction speed to that of human hands. Even incredibly dumb algorithms will consistently beat humans when dexterity is king, so just showing that an AI is better than a human at a task doesn't necessarily mean that it's smarter than a human at that task.

[Brambazai]

Personally, I'd like to see AI's playing Planetary Annihilation

[coderxff]

I think that this is a much bigger deal than a lot of the other stuff we've seen. I'd even go so far as to say that it warrants more than two minutes! Unfortunately, there are no videos from the paper demonstrating game play. I'm looking forward to demonstrations in real-world domains.

[zubrz]

but you told 0 information about the algorithm itself : (

[Kave]

"requires a great deal of mechanical skill, split-second decision making (and imperfect information)" sounds like EXACTLY what AIs should be better at than humans

[GhostkillerPlaysMC]

We need to see MuZero’s highest round in Nazi Zombies

[connor-shorten]

Great video! I am exploring MuZero this week as well in a series going from AlphaGo --> AlphaGo Zero --> AlphaZero --> MuZero! I hope attention around MuZero and these algorithms will also inspire more people to participate in Kaggle's Connect X 1st RL Competition!

[MichaelSHartman]

I haven't heard much about generalization levels of AI. Given we will not reach it fully overnight, is there a scale, or grading system for generalization? Did the learning time decrease, or ability decrease or increase?

[SouravTechLabs]

That's awesome @Two Minutes AI Papers

[beepzdr]

Will it lose performance on game A if you trained it on A then train the existing network on B?

[Dogbertforpresident]

Can't believe this has not been on the news.