↓ Skip to main content

Mastering the game of Go with deep neural networks and tree search

Overview of attention for article published in Nature, January 2016
Altmetric Badge

About this Attention Score

  • In the top 5% of all research outputs scored by Altmetric
  • Among the highest-scoring outputs from this source (#24 of 46,384)
  • High Attention Score compared to outputs of the same age (99th percentile)
  • High Attention Score compared to outputs of the same age and source (99th percentile)

Readers on

mendeley
4110 Mendeley
citeulike
24 CiteULike
Title
Mastering the game of Go with deep neural networks and tree search
Published in
Nature, January 2016
DOI 10.1038/nature16961
Pubmed ID
Authors

David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis, Silver, David, Huang, Aja, Maddison, Chris J, Guez, Arthur, Sifre, Laurent, van den Driessche, George, Schrittwieser, Julian, Antonoglou, Ioannis, Panneershelvam, Veda, Lanctot, Marc, Dieleman, Sander, Grewe, Dominik, Nham, John, Kalchbrenner, Nal, Sutskever, Ilya, Lillicrap, Timothy, Leach, Madeleine, Kavukcuoglu, Koray, Graepel, Thore, Hassabis, Demis

Abstract

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses 'value networks' to evaluate board positions and 'policy networks' to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

Twitter Demographics

The data shown below were collected from the profiles of 1,899 tweeters who shared this research output. Click here to find out more about how the information was compiled.

Mendeley readers

The data shown below were compiled from readership statistics for 4,110 Mendeley readers of this research output. Click here to see the associated Mendeley record.

Geographical breakdown

Country Count As %
United States 107 3%
United Kingdom 52 1%
Germany 38 <1%
Japan 26 <1%
China 19 <1%
Spain 11 <1%
Korea, Republic of 11 <1%
Netherlands 11 <1%
Canada 10 <1%
Other 106 3%
Unknown 3719 90%

Demographic breakdown

Readers by professional status Count As %
Student > Ph. D. Student 1183 29%
Student > Master 831 20%
Researcher 699 17%
Student > Bachelor 447 11%
Other 201 5%
Other 552 13%
Unknown 197 5%
Readers by discipline Count As %
Computer Science 1939 47%
Engineering 596 15%
Agricultural and Biological Sciences 317 8%
Physics and Astronomy 262 6%
Mathematics 129 3%
Other 670 16%
Unknown 197 5%

Attention Score in Context

This research output has an Altmetric Attention Score of 3116. This is our high-level measure of the quality and quantity of online attention that it has received. This Attention Score, as well as the ranking and number of research outputs shown below, was calculated when the research output was last mentioned on 25 May 2017.
All research outputs
#64
of 7,770,131 outputs
Outputs from Nature
#24
of 46,384 outputs
Outputs of similar age
#7
of 327,990 outputs
Outputs of similar age from Nature
#3
of 966 outputs
Altmetric has tracked 7,770,131 research outputs across all sources so far. Compared to these this one has done particularly well and is in the 99th percentile: it's in the top 5% of all research outputs ever tracked by Altmetric.
So far Altmetric has tracked 46,384 research outputs from this source. They typically receive a lot more attention than average, with a mean Attention Score of 71.6. This one has done particularly well, scoring higher than 99% of its peers.
Older research outputs will score higher simply because they've had more time to accumulate mentions. To account for age we can compare this Altmetric Attention Score to the 327,990 tracked outputs that were published within six weeks on either side of this one in any source. This one has done particularly well, scoring higher than 99% of its contemporaries.
We're also able to compare this research output to 966 others from the same source and published within six weeks on either side of this one. This one has done particularly well, scoring higher than 99% of its contemporaries.