[computer-go] Combining Online and Offline Knowledge in UCT

After much effort, I think I understand most of the Gelly&Shriver paper[1]. I'm hoping this post will help others and possibly have people correct any errors I've made. First, some basic definitions of notation: * In general, "Q" is an estimated winning rate, used in three ways: 1. As an estimat

Ang: [computer-go] Combining online and offline knowledge in UCT

Reinforcment Learning: A Survey is available on citeseer. /Dan Andersson Ursprungligt meddelande Från: [EMAIL PROTECTED] Datum: 2007-okt-12 02:18 Till: "computer-go" Ärende: [computer-go] Combining online and offline knowledge in UCT Does anyone have a good reference for r

[computer-go] Combining online and offline knowledge in UCT

Does anyone have a good reference for reading the notation in the Gelley/Shriver paper "Combining online and offline knowledge in UCT"? ___ computer-go mailing list computer-go@computer-go.org http://www.computer-go.org/mailman/listinfo/computer-go/