Residual Networks for Computer Go
Cazenave, Tristan (2018), Residual Networks for Computer Go, IEEE Transactions on Games, 10, 1, p. 107-110. 10.1109/TCIAIG.2017.2681042
TypeArticle accepté pour publication ou publié
Journal nameIEEE Transactions on Games
IEEE - Institute of Electrical and Electronics Engineers
MetadataShow full item record
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)Deep learning for the game of Go recently had a tremendous success with the victory of AlphaGo against Lee Sedol in March 2016. We propose to use residual networks so as to improve the training of a policy network for computer Go. Training is faster than with usual convolutional networks and residual networks achieve high accuracy on our test set and a four dan level.
Subjects / KeywordsComputer Go; deep learning; residual networks
Showing items related by title and author.