If you are seeking the proof that UCT converges (in stochastic sense) to an optimal solution if enough time is give is in the original paper of UCT algorithm, ecml06.pdf by Levente Kocsis and Csaba Szepesvari. You can find it by Google.
Hideki Willemien: <[email protected]>: >On life in 19x 19 http://www.lifein19x19.com/forum/viewtopic.php?p=37588#p37588 > >i found the statement >. >" I think there exists a proof that MCTS gives the same results as >normal minimax search when the number of playouts goes to infinity." > >Does this proof really exist and where can i find it? > >also because MCTS still needs to learn to work with draws How can it be true? >_______________________________________________ >Computer-go mailing list >[email protected] >http://dvandva.org/cgi-bin/mailman/listinfo/computer-go -- Hideki Kato <mailto:[email protected]> _______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
