MuZero’s first step from research into the real world

Collaborating with YouTube to optimise video compression in the open source VP9 codec.

February 11, 2022 Research MuZero Applied Team Collaborating with YouTube to optimise video compression in the open source VP9 codec. In 2016, we introduced AlphaGo, the first artificial intelligence program to defeat humans at the ancient game of Go. Its successors, AlphaZero and then MuZero, each represented a significant step forward in the pursuit of general-purpose algorithms, mastering a greater number of games with even less predefined knowledge. MuZero, for example, mastered Chess, Go, Shogi, and Atari without needing to be told the rules. But so far these agents have focused on…

related reading

• The First Fully General Computer Action Model | blogsi.inc
• Deriving Muonjeremybernste.in
• [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
• TurboQuant: Redefining AI efficiency with extreme compressionresearch.google
• Competitive programming with AlphaCode — Google DeepMinddeepmind.com
• AlphaGo Zero: Minimal Policy Improvement, Expectation Propagation and other Connectionsinference.vc
• Simple Alpha Zeroweb.stanford.edu
• Video models are zero-shot learners and reasonersarxiv.org
• Muon: An optimizer for hidden layers in neural networks | Keller Jordan blogkellerjordan.github.io
• TurboQuant: Redefining AI efficiency with extreme compressionresearch.google
• [2206.11795] Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videosarxiv.org
• Compression and Intelligencegreene.sh