{"id":9816,"date":"2019-02-07T09:00:17","date_gmt":"2019-02-07T09:00:17","guid":{"rendered":"https:\/\/microsites.bournemouth.ac.uk\/cel\/?p=9816"},"modified":"2019-01-29T10:03:14","modified_gmt":"2019-01-29T10:03:14","slug":"googles-ai-surfs-the-gamescape-to-conquer-game-theory","status":"publish","type":"post","link":"https:\/\/microsites.bournemouth.ac.uk\/flie\/2019\/02\/07\/googles-ai-surfs-the-gamescape-to-conquer-game-theory\/","title":{"rendered":"Google\u2019s AI surfs the \u201cgamescape\u201d to conquer game theory"},"content":{"rendered":"

Following on their victory in StarCraft II, Google’s DeepMind researchers lay out a plan to find diversity in players of games to get around the problems of hidden information in game theory. Their work points to a kind of “open-ended learning” that surpasses simple test-taking found in most machine learning.<\/p>\n

\n

The miracle of AI in the realm of playing games is encapsulated in the AlphaGo Zero program, which\u00a0in 2017 was able to beat all human players<\/a>\u00a0of the ancient strategy game strictly by what’s called “self-play,” exploring different possible moves without any human tips. A revised version, AlphaZero, gained such general knowledge that\u00a0it can now excel at not only Go<\/a>\u00a0but also chess and the game\u00a0Shogi<\/a>, Japan’s version of chess.<\/p>\n

Hence, neural nets can generalize across many games just by self-play.<\/p>\n

But not all games, it turns out. There are some games that don’t lend themselves to the AlphaZero approach, games known technically as being “intransitive.”<\/p>\n

For these games, Google’s DeepMind AI researchers have figured out a new trick, a way of constructing a kind of super athlete by seeking diversity of moves and styles of play. The primary example, AlphaStar, recently won a match against the best human player of the strategy video game StarCraft II,\u00a0as ZDNet chronicled last week<\/a>.<\/p>\n<\/div>\n

 <\/p>\n

READ MORE HERE >>><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"

Following on their victory in StarCraft II, Google’s DeepMind researchers lay out a plan to find diversity in players of games to get around the problems of hidden information in game theory. Their work points to a kind of “open-ended learning” that surpasses simple test-taking found in most machine learning. The miracle of AI in… Read more » about Google\u2019s AI surfs the \u201cgamescape\u201d to conquer game theory<\/span><\/a><\/p>\n","protected":false},"author":525,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[5],"tags":[],"class_list":["post-9816","post","type-post","status-publish","format-standard","hentry","category-news"],"acf":[],"_links":{"self":[{"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/posts\/9816","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/users\/525"}],"replies":[{"embeddable":true,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/comments?post=9816"}],"version-history":[{"count":1,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/posts\/9816\/revisions"}],"predecessor-version":[{"id":9817,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/posts\/9816\/revisions\/9817"}],"wp:attachment":[{"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/media?parent=9816"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/categories?post=9816"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/microsites.bournemouth.ac.uk\/flie\/wp-json\/wp\/v2\/tags?post=9816"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}