Demystifying AlphaGo

MSc Essay

Adnan Reza

Essay PDF and Slides

Lee Sedol vs Alpha Go | Match Summaries


1 Bouzy, Bruno, and Tristan Cazenave. "Computer Go: an AI oriented survey." Artificial Intelligence 132.1 (2001): 39-103
2 Silver, David, et al. "Mastering the game of Go with deep neural networks and tree search." nature 529.7587 (2016): 484-489.
3 Byford, Sam. “Google's AlphaGo AI Defeats World Go Number One Ke Jie.” The Verge, The Verge, 23 May 2017, alphago-ke-jie-match-google-deepmind-ai-2017.
4 Müller, Martin. "Computer go." Artificial Intelligence 134.1-2 (2002): 145-179.
5 Hölldobler, Steffen, Sibylle Möhle, and Anna Tigunova. "Lessons Learned from AlphaGo."
6 Osborne, Martin J., and Ariel Rubinstein. A course in game theory. MIT press, 1994.
7 Schaeffer, Jonathan, et al. "Solving checkers." Proceedings of the 19th international joint conference on Artificial intelligence. Morgan Kaufmann Publishers Inc., 2005.
8 Maddison, Chris J., et al. "Move evaluation in go using deep convolutional neural networks." arXiv preprint arXiv:1412.6564(2014).
9 Van Den Herik, H. Jaap, Jos WHM Uiterwijk, and Jack Van Rijswijck. "Games solved: Now and in the future." Artificial Intelligence 134.1-2 (2002): 277-311.
10 Remus, Horst. "Simulation of a Learning Machine for Playing GO." IFIP Congress. 1962.
11 Zobrist, Albert L. "A model of visual organization for the game of GO." Proceedings of the May 14-16, 1969, spring joint computer conference. ACM, 1969.
12 Zobrist, Albert Lindsey. "Feature extraction and representation for pattern recognition and the game of go." (1970).
13 Reitman, Walter, and Bruce Wilcox. "The structure and performance of the Interim. 2 Go program." Proceedings of the 6th international joint conference on Artificial intelligence-Volume 2. Morgan Kaufmann Publishers Inc., 1979.
14 Boon, Mark. "A pattern matcher for Goliath." Computer go 13 (1989): 12-23.
15 Brügmann, Bernd. Monte carlo go. Vol. 44. Syracuse, NY: Technical report, Physics Department, Syracuse University, 1993.
16 Coulom, Rémi. "Efficient selectivity and backup operators in Monte-Carlo tree search." International conference on computers and games. Springer, Berlin, Heidelberg, 2006.
17 Sutskever, Ilya, and Vinod Nair. "Mimicking go experts with convolutional neural networks." International Conference on Artificial Neural Networks. Springer, Berlin, Heidelberg, 2008.
18 Clark, Christopher, and Amos Storkey. "Training deep convolutional neural networks to play go." International Conference on Machine Learning. 2015.
19 Kocsis, Levente, and Csaba Szepesvári. "Bandit based monte-carlo planning." European conference on machine learning. Springer, Berlin, Heidelberg, 2006.
20 Chaslot, Guillaume, et al. "Monte-Carlo Tree Search: A New Framework for Game AI." AIIDE. 2008.
21 Burger, Christopher. “Google DeepMind's AlphaGo: How It Works.” On Personalization and Data, 6 Feb. 2017, alphago-how-it-works/
22 Tesauro, Gerald. "Td-gammon: A self-teaching backgammon program." Applications of Neural Networks. Springer, Boston, MA, 1995. 267-285.
23 W Schubert. KGS Go server, 2010.
24 Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. Vol. 1. No. 1. Cambridge: MIT press, 1998.
25 Littman, Michael L. "Markov games as a framework for multi-agent reinforcement learning." Machine Learning Proceedings 1994. 1994. 157-163.
26 Campbell, Murray, A. Joseph Hoane Jr, and Feng-hsiung Hsu. "Deep blue." Artificial intelligence 134.1-2 (2002): 57-83.
27 Silver, David, et al. "Mastering the game of go without human knowledge." Nature 550.7676 (2017): 354
28 Condliffe, Jamie. “DeepMind's Groundbreaking AlphaGo Zero AI Is Now a Versatile Gamer.” MIT Technology Review, MIT Technology Review, 6 Dec. 2017, alphago-zero-ai-is-now-a-versatile-gamer/.
29 “AlphaGo Zero: Learning from Scratch.” DeepMind, zero-learning-scratch/.