Thursday, March 10, 2016

AlphaGo and deep mind


https://deepmind.com/alpha-go.html

DeepMind replication
https://github.com/Rochester-NRT/AlphaGo



Mastering the game of Go with deep neural networks and tree search
https://drive.google.com/file/d/0B11ZqB11tZ92alI4X1RBc0hQX28/view?usp=sharing_eid&ts=56e1bd00

Kocsis and Szepesvari, Bandit based Monte-Carlo Planning
https://drive.google.com/file/d/0B11ZqB11tZ92a09vZVIzd25fRDQ/view?usp=sharing

More publications
https://deepmind.com/publications.html

No comments:

Post a Comment