Move Evaluation in Go Using Deep Convolutional Neural Networks

Chris J. Maddison; Aja Huang; Ilya Sutskever; David Silver

doi:10.48550/arxiv.1412.6564

Abstract

The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, it beat the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art Monte-Carlo tree search that simulates a million positions per move.

Keywords

Monte Carlo tree searchComputer scienceConvolutional neural networkArtificial intelligenceDeep learningMachine learningMonte Carlo method

Affiliated Institutions

Related Publications

Planning chemical syntheses with deep neural networks and symbolic AI

Marwin Segler , Mike Preuß , Mark P. Waller

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingl...

2018 Nature 1780 citations

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

David Silver , Thomas Hubert , Julian Schrittwieser +10 more

One program to rule them all Computers can beat humans at increasingly complex games, including chess and Go. However, these programs are typically constructed for a particular ...

2018 Science 3322 citations

GameFlow

Penelope Sweetser , Peta Wyeth

Although player enjoyment is central to computer games, there is currently no accepted model of player enjoyment in games. There are many heuristics in the literature, based on ...

2005 Computers in entertainment 2008 citations

Playing Atari with Deep Reinforcement Learning

Alex Graves , Ioannis Antonoglou , Daan Wierstra +4 more

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolu...

2013 arXiv (Cornell University) 5109 citations

Methods for Evaluating Gameplay Experience in a Serious Gaming Context.

Lennart E. Nacke , Anders Drachen , Stefan Göbel

Gameplay experience (GX) is created during the process of player-game interaction, where this interaction has the goal to provide a motivating, fun experience for the player. Si...

2010 141 citations

Publication Info

Year: 2014
Type: article
Citations: 92
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Move Evaluation in Go Using Deep Convolutional Neural Networks

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

OpenAlex

Cite This

APA Style

                            
                                    Chris J. Maddison, 
                                
                                    Aja Huang, 
                                
                                    Ilya Sutskever
                                
                                et al.
                            
                            (2014). 
                            Move Evaluation in Go Using Deep Convolutional Neural Networks. 
                            arXiv (Cornell University)
                            
                            .
                            https://doi.org/10.48550/arxiv.1412.6564

Identifiers

DOI: 10.48550/arxiv.1412.6564