# AlphaGo Zero learns from nothing

Date: 18 October 2017 · Era: V · Transformers · Category: model · Significance: 4/5
People: David Silver, Julian Schrittwieser, Demis Hassabis
Organisations: DeepMind

Canonical: https://shapeofintelligence.com/timeline/2017-alphago-zero/ · Dataset and text CC BY 4.0

> A new version starts from random play with no human games at all, and after three days beats the AlphaGo that beat Lee Sedol 100 games to 0.

## What had to happen

31 events back to 1943, oldest first. Direct influences are marked *direct*.

- [1943 · A logical calculus of nervous activity](https://shapeofintelligence.com/md/timeline/1943-mcculloch-pitts-neuron/)
- [1948 · A mathematical theory of communication](https://shapeofintelligence.com/md/timeline/1948-shannon-information-theory/)
- [1949 · Cells that fire together wire together](https://shapeofintelligence.com/md/timeline/1949-hebb-organization-of-behavior/)
- [1950 · Programming a computer for playing chess](https://shapeofintelligence.com/md/timeline/1950-shannon-chess/)
- [1958 · The perceptron learns](https://shapeofintelligence.com/md/timeline/1958-perceptron/)
- [1959 · Samuel's checkers program coins 'machine learning'](https://shapeofintelligence.com/md/timeline/1959-samuel-machine-learning/)
- [1960 · ADALINE and the least-mean-squares rule](https://shapeofintelligence.com/md/timeline/1960-adaline-lms/)
- [1965 · Moore's law](https://shapeofintelligence.com/md/timeline/1965-moores-law/)
- [1969 · Perceptrons](https://shapeofintelligence.com/md/timeline/1969-perceptrons-book/)
- [1970 · Reverse-mode automatic differentiation](https://shapeofintelligence.com/md/timeline/1970-linnainmaa-backprop/)
- [1974 · Werbos applies backpropagation to neural networks](https://shapeofintelligence.com/md/timeline/1974-werbos-backprop/)
- [1980 · The Neocognitron](https://shapeofintelligence.com/md/timeline/1980-neocognitron/)
- [1982 · The Hopfield network](https://shapeofintelligence.com/md/timeline/1982-hopfield-network/)
- [1985 · The Boltzmann machine](https://shapeofintelligence.com/md/timeline/1985-boltzmann-machine/)
- [1986 · Backpropagation](https://shapeofintelligence.com/md/timeline/1986-backpropagation/)
- [1988 · Temporal-difference learning](https://shapeofintelligence.com/md/timeline/1988-temporal-difference-learning/)
- [1989 · Q-learning](https://shapeofintelligence.com/md/timeline/1989-q-learning/)
- [1989 · LeNet reads handwritten postcodes](https://shapeofintelligence.com/md/timeline/1989-lenet/)
- [1990 · Finding structure in time](https://shapeofintelligence.com/md/timeline/1990-elman-network/)
- [1991 · The vanishing gradient problem](https://shapeofintelligence.com/md/timeline/1991-vanishing-gradient/)
- [1992 · TD-Gammon reaches world-class backgammon](https://shapeofintelligence.com/md/timeline/1992-td-gammon/) *direct*
- [1998 · MNIST and LeNet-5](https://shapeofintelligence.com/md/timeline/1998-mnist-lenet5/)
- [1999 · The first GPU](https://shapeofintelligence.com/md/timeline/1999-geforce-256/)
- [2006 · Deep belief networks and the word 'deep'](https://shapeofintelligence.com/md/timeline/2006-deep-belief-nets/)
- [2007 · CUDA](https://shapeofintelligence.com/md/timeline/2007-cuda/)
- [2009 · ImageNet](https://shapeofintelligence.com/md/timeline/2009-imagenet/)
- [2010 · Rectified linear units](https://shapeofintelligence.com/md/timeline/2010-relu/)
- [2012 · Dropout](https://shapeofintelligence.com/md/timeline/2012-dropout/)
- [2012 · AlexNet wins ImageNet](https://shapeofintelligence.com/md/timeline/2012-alexnet/)
- [2013 · Deep Q-networks play Atari](https://shapeofintelligence.com/md/timeline/2013-dqn/)
- [2016 · AlphaGo beats Lee Sedol](https://shapeofintelligence.com/md/timeline/2016-alphago/) *direct*

The original AlphaGo had started from thirty million moves by human experts. The version published in Nature on 18 October 2017 started from nothing. A single network, given only the rules, played itself, and at every move used tree search to improve on its own raw guess; the improved move became the training target, and the game's outcome trained the value. After three days and 4.9 million games it beat the Lee Sedol version 100 games to nil, and after forty days it beat the version that had defeated the world number one, Ke Jie, earlier that year.

It also rediscovered Go. Its self-play games passed through the standard human openings and beyond them, and some joseki that players had used for centuries it abandoned as inferior. Its successor AlphaZero, two months later, learned chess and shogi the same way in hours and beat the strongest engines.

AlphaGo Zero is the purest demonstration on this timeline of Sutton's bitter lesson before he wrote it: remove the human knowledge, add compute and self-play, and the result is stronger. It is also TD-Gammon's method vindicated twenty-five years on, and the origin of the search-plus-learning loop that reasoning models revived for language in 2024.

## What it led to

9 events downstream, through 2026.

Built on it directly:

- [2024 · o1 and reasoning models](https://shapeofintelligence.com/md/timeline/2024-o1/)

And, through them, by era:

- VII · Agents: 8 events

## Sources

- [Mastering the game of Go without human knowledge (Nature, 2017)](https://doi.org/10.1038/nature24270) — paper

---

The Shape of Intelligence by Jamie McKaye (https://jamiemckaye.com) · Markdown mirror of https://shapeofintelligence.com/timeline/2017-alphago-zero/

Before: [2017 · Deep reinforcement learning from human preferences](https://shapeofintelligence.com/md/timeline/2017-rl-from-human-preferences/) · After: [2018 · GPT: generative pre-training](https://shapeofintelligence.com/md/timeline/2018-gpt-1/)
