AA << introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher >>
David Silver, Julian Schrittwieser et al. Mastering the game of Go without human knowledge. Nature. 2017; 550: 354–9 doi: 10.1038/nature24270 Oct 18, 2017
http://www.nature.com/nature/journal/v550/n7676/full/nature24270.html
also
# s-ai: handling imperfect information (from scratch), by Libratus. Feb 4, 2017.
http://flashontrack.blogspot.it/2017/02/s-ai-handling-imperfect-information.html