Tag: ai

MuZero Intuition

To celebrate the publication of our MuZero paper in [cached]Nature ([cached]full-text), I've written a high level description of the MuZero algorithm. My focus here is to give you an intuitive understanding and general overview of the algorithm; for the full details please read the paper. Please also see our [cached]official DeepMind blog post, it has great animated versions of the figures!

MuZero is a very exciting step forward - it requires no special knowledge of game rules or environment dynamics, instead learning a model of the environment for itself and using this model to plan. Even though it …


MuZero talk - ICAPS 2020

I gave a detailed talk about MuZero at ICAPS 2020, at the workshop "Bridging the Gap Between AI Planning and Reinforcement Learning".

In addition to giving an overview of the algorithm in general, I also went into more detail about reanalyse - the technique that allows MuZero to use the model based search to repeatedly learn more from the same episode data.

I hope you find the talk useful! I've also uploaded my slides for easy reference.


Getting into Machine Learning - 2020

My previous Getting into Machine Learning post is one of my most popular; since then much has changed.

There's a new kid on the block: [cached]JAX. A thin, but powerful layer over Autograd and XLA, it makes it easy to concisely express algorithms with the same syntax as numpy while getting the full performance of TPUs and GPUs.

Especially in combination with higher level libraries such as [cached]Haiku, JAX makes it fun and easy to try new ideas. I've migrated all my own research to JAX and can only recommend it!

The resources I recommended in my previous …


The Case Against the Singularity

From Musk's "Potentially more dangerous than nukes." tweet, increased funding for the Machine Intelligence Research Institute (MIRI) to the founding of cross-industry groups like the Partnership on AI, AI is being taken more seriously.

One worry that is sometimes cited, as in the book [cached]Superintelligence by Nick Bostrom, is that once we reach human-level AI, it might rapidly improve itself past anything humans can envision, becoming impossible to control. This is called "Singularity", because anything after such a point is unforseeable.

The argument for a Singularity rests on the fact that a hypothetical AI could devote all its resources …


MuZero - Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

I'm excited to finally share some more details on what we've been working on since AlphaZero.

Recently, we made our latest paper - Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model, aka MuZero - available on arXiv:

Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go, where a perfect simulator is available. However, in real-world problems the dynamics governing the environment are often complex and unknown. In this work we present the MuZero …


Getting into Machine Learning

Update: I've published a newer version of this post.

If you are interested in getting started with Machine Learning, the [cached]TensorFlow Playground is a good way of building some intuition.

For a first introduction to the field, I recommend [cached]Neural Networks and Deep Learning, followed by the [cached]Deep Learning book.

To dive into a specific topic quickly, the [cached]TensorFlow tutorials are also great, Dive into Deep Learning has a lot of detail as well.

For Reinforcement Learning specifically, the standard text is [cached]Reinforcement Learning: An Introduction. Dave's [cached]UCL Course on RL is great too …


AlphaGo Documentary

As some of you may have noticed, the [cached]AlphaGo documentary is now available on [cached]Play Movies and [cached]Netflix!

It's a great documentary and really captures the history of AlphaGo very well - every time I watch it it takes me right back to the excitement of those months! If you are interested in AI, Go, or just like documentaries in general I really recommend you give it a try.


AlphaGo Zero

Usually in software, version numbers tend to go up, not down. With AlphaGo Zero, we did the opposite - by taking out handcrafted human knowledge, we ended up with both a simpler and more beautiful algorithm and a stronger Go program.

We provide a full description in our paper, Mastering the game of Go without human knowledge, which you can also read online.

At the core is a self-improvement loop based on self-play and Monte Carlo Tree Search (MCTS): We start with a randomly initialized network, then use this network in the MCTS to play the first games. The network is …


AlphaGo in China

You might have heard about our [cached]recent games with AlphaGo in China, at the Future of Go summit. No only did we play the legendary Ke Jie, but there were also two new and exciting formats: Team Go and Pair Go.

This match was also very exciting on the technical side because we had improved AlphaGo to the point where we ran it on [cached]a single machine in the Google Cloud - that's [cached]one tenth of the computation power compared to the distributed version we used in the last match!

Personally, I also really enjoyed the Pair Go …


AlphaGo - Lee Se-dol

After 5 long and exciting games AlphaGo finally managed to win 4:1 against the legendary Lee Se-dol, the first time in history a computer program managed to defeat a 9 dan professional player in an even match. And not just any 9 dan player, probably the best player of the decade. It was even awarded an honorary rank of 9 dan professional itself!

Obviously we are all extremely proud of this achievement, you can find out more about the details in our Nature paper. Most importantly, we still used roughly the same amount of hardware! This was a true …

© Julian Schrittwieser. Built using Pelican. Theme by Giulio Fidente on github. .