Artificial intelligence: Learning to play Go from scratch

@article{Singh2017ArtificialIL,
  title={Artificial intelligence: Learning to play Go from scratch},
  author={Satinder Singh and Andy Okun and Andrew Jackson},
  journal={Nature},
  year={2017},
  volume={550},
  pages={336-337}
}
An artificial-intelligence program called AlphaGo Zero has mastered the game of Go without any human data or guidance. A computer scientist and two members of the American Go Association discuss the implications. See Article p.354 To beat world champions at the game of Go, the computer program AlphaGo has relied largely on supervised learning from millions of human expert moves. David Silver and colleagues have now produced a system called AlphaGo Zero, which is based purely on reinforcement… 
View on Springer
ncbi.nlm.nih.gov
60 Citations
Highly Influential Citations
2
Background Citations
20
Methods Citations
2

60 Citations

Collective behavior of artificial intelligence population: transition from optimization to game

The reinforcement learning (RL) algorithm is introduced into minority game (MG) dynamics, in which agents have learning ability based on one typical RL scheme, Q-learning, and the critical curve for transition between the two mechanisms in phase diagram is obtained analytically.

Collective behavior of artificial intelligence population: transition from optimization to game

It is found that through short-term training, the multi-agent AI system adopting Q-learning algorithm relaxes to the optimal solution of the game and one striking phenomenon is the transition of interaction mechanism from self-organized optimization to game through tuning the fraction of RL agents.

How to make Artificial Wisdom possible

  • H. Nusbaum
  • Psychology
    International Psychogeriatrics
  • 2020
In advocating for the development of Artificial Wisdom (AW), Jeste et al. (2020) lay a foundation in understanding intelligence and wisdom and their importance to humanity. They outline the…

Neural Networks Models for Analyzing Magic: the Gathering Cards

This work aims to apply neural networks models, including Convolutional Neural Networks and Recurrent Neural Networks, in order to analyze Magic: the Gathering cards, both in terms of card text and illustrations, and develop a methodology that could generate card text matching it to an input image.

Humanly Certifying Superhuman Classifiers

A theory for estimating the accuracy compared to the oracle, using only imperfect human annotations for reference is developed and the utility of the theory is demonstrated by meta-analyzing large-scale natural language processing tasks.

How to make Arti fi cial Wisdom possible

  • Psychology
  • 2020
In advocating for the development of Artificial Wisdom (AW), Jeste et al. (2020) lay a foundation in understanding intelligence and wisdom and their importance to humanity. They outline the…

The Go Transformer: Natural Language Modeling for Game Play

The Generative Pretrained Transformer (GPT-2) is trained to mimic the style of Go champions as archived in Smart Game Format, which offers a text description of move sequences.

A.I. Ethics in the City

The big city, I contend, will be the site where complex A.I ethics conflicts will emerge most prominently; in different ways in different parts of the world.

Artificial Intelligence Can’t Be Charmed: The Effects of Impartiality on Laypeople’s Algorithmic Preferences

Over the coming years, AI could increasingly replace humans for making complex decisions because of the promise it holds for standardizing and debiasing decision-making procedures. Despite intense…

Applying machine learning in science assessment: a systematic review

This study identifies existing research gaps and suggests that all three vertices of the ML triangle should be addressed in future assessment studies, with an emphasis on the pedagogy and technology features.
...

References

SHOWING 1-6 OF 6 REFERENCES

Mastering the game of Go without human knowledge

An algorithm based solely on reinforcement learning is introduced, without human data, guidance or domain knowledge beyond game rules, that achieves superhuman performance, winning 100–0 against the previously published, champion-defeating AlphaGo.

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

Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.

The grand challenge of computer Go

This paper describes the leading algorithms for Monte-Carlo tree search and explains how they have advanced the state of the art in computer Go.

Temporal difference learning and TD-Gammon

The domain of complex board games such as Go, chess, checkers, Othello, and backgammon has been widely regarded as an ideal testing ground for exploring a variety of concepts and approaches in artificial intelligence and machine learning.

Deep Blue

Temporal-difference search in computer Go

This work applies temporal-difference search to the game of 9×9 Go, using a million binary features matching simple patterns of stones, and outperformed an unenhanced Monte-Carlo tree search with the same number of simulations.