Mastering the game of Go without human knowledge

David Silver, Julian Schrittwieser, Karen Simonyan, Demis Hassabis · 17 authors total from DeepMind; key names listed, final senior author Demis Hassabis included.

Published 19 October 2017 · Nature · Journal article

Read the original paper Cite

Summary

This paper presented AlphaGo Zero, which learned to play Go solely through self-play reinforcement learning without any human game data or handcrafted features, using a single neural network and a simpler tree search. Starting from random play, it discovered Go knowledge and novel strategies on its own. AlphaGo Zero surpassed all previous versions of AlphaGo, including the one that beat Lee Sedol.

Key findings

Learned Go entirely from self-play with no human knowledge or supervised data.
Used a single combined policy/value network and simplified Monte Carlo tree search.
Defeated the previous champion-beating AlphaGo version 100-0.

Subjects & keywords

Artificial Intelligence reinforcement learning self-play monte carlo tree search alphago zero game of go

Cite this paper

APA

David Silver, Julian Schrittwieser, Karen Simonyan, & Demis Hassabis [17 authors total from DeepMind; key names listed, final senior author Demis Hassabis included.] (2017). Mastering the game of Go without human knowledge. Nature. https://doi.org/10.1038/nature24270

BibTeX

@article{silver2017mastering,
  author    = {David Silver and Julian Schrittwieser and Karen Simonyan and Demis Hassabis and {17 authors total from DeepMind; key names listed, final senior author Demis Hassabis included.}},
  title     = {Mastering the game of Go without human knowledge},
  journal   = {Nature},
  year      = {2017},
  doi       = {10.1038/nature24270},
  url       = {https://doi.org/10.1038/nature24270}
}

Related in Artificial Intelligence

AI2023

Segment Anything

Alexander Kirillov, Eric Mintun and Nikhila Ravi

This paper introduces the Segment Anything project: a promptable image segmentation task, the Segment Anything Model (SAM), and the SA-1B dataset. SAM combines an image encoder, a flexible prompt encoder (points, boxes, masks, text), and a fast mask decoder to produce valid segmentation masks from arbitrary prompts. Trained on over 1 billion masks across 11 million images, SAM shows strong zero-shot transfer to many segmentation tasks without additional training.

IEEE/CVF International Conference on Computer Vision (ICCV) Open access

AI2023

GPT-4 Technical Report

OpenAI

This technical report describes GPT-4, a large-scale multimodal Transformer model that accepts image and text inputs and produces text outputs. The report emphasizes that GPT-4 achieves human-level performance on a range of professional and academic benchmarks, and details infrastructure and optimization methods that allowed performance to be predicted from much smaller models. For competitive and safety reasons, the report withholds architecture, dataset, and training details.

arXiv Open access

AI2023

LLaMA: Open and Efficient Foundation Language Models

Hugo Touvron, Thibaut Lavril and Gautier Izacard

The paper presents LLaMA, a family of foundation language models ranging from 7B to 65B parameters trained exclusively on publicly available datasets. It argues that strong performance can be reached without proprietary data and at smaller parameter counts than prior models. LLaMA-13B outperforms the much larger GPT-3 175B on most benchmarks, and LLaMA-65B is competitive with the best contemporary models such as Chinchilla-70B and PaLM-540B.

arXiv preprint (arXiv:2302.13971) Open access