AlphaGo Zero: algorithms over data and compute

Written by: Stephen Hsu

Primary Source:  Information Processing

AlphaGo Zero was trained entirely through self-play — no data from human play was used. The resulting program is the strongest Go player ever by a large margin, and is extremely efficient in its use of compute (running on only 4 TPUs).

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0.

Rapid progress from a random initial state is rather amazing, but perhaps something we should get used to given that:

1. Deep Neural Nets are general enough to learn almost any function (i.e., high dimensional mathematical function) no matter how complex
2. The optimization process is (close to) convex

A widely discussed AI mystery: how do human babies manage to learn (language, intuitive physics, theory of mind) so quickly and with relatively limited training data? AlphaGo Zero’s impressive results are highly suggestive in this context — the right algorithms make a huge difference.

It seems certain that great things are coming in the near future…

The following two tabs change content below.
Stephen Hsu
Stephen Hsu is vice president for Research and Graduate Studies at Michigan State University. He also serves as scientific adviser to BGI (formerly Beijing Genomics Institute) and as a member of its Cognitive Genomics Lab. Hsu’s primary work has been in applications of quantum field theory, particularly to problems in quantum chromodynamics, dark energy, black holes, entropy bounds, and particle physics beyond the standard model. He has also made contributions to genomics and bioinformatics, the theory of modern finance, and in encryption and information security. Founder of two Silicon Valley companies—SafeWeb, a pioneer in SSL VPN (Secure Sockets Layer Virtual Private Networks) appliances, which was acquired by Symantec in 2003, and Robot Genius Inc., which developed anti-malware technologies—Hsu has given invited research seminars and colloquia at leading research universities and laboratories around the world.
Stephen Hsu

Latest posts by Stephen Hsu (see all)