I would just mention that Maven/Scrabble truncated rollouts are not comparable to Go/MCTS truncated rollouts. An evaluation function in Scrabble is readily at hand, because scoring points is hugely correlated with winning. There is no evaluation function for Go that is readily at hand.
There have been some efforts at whole-board evaluation in Go. Maybe NeuroGo was the earliest really cool demonstration. But I never saw anything that gave me confidence that the approach could work when embedded in an MCTS framework. I am blown away. -----Original Message----- From: Computer-go [mailto:[email protected]] On Behalf Of "Ingo Althöfer" Sent: Thursday, January 28, 2016 1:00 AM To: [email protected] Subject: Re: [Computer-go] Game Over Hello Anders, thanks for the summary on the smartgo site. > ... the truncated rollouts mentioned in the paper are still unclear to me. The greatest expert on these rollouts might be Richard Lorentz. He applied them successfully to his bots in the games Amazons (not to be mixed up with the online bookshop), Havannah and Breakthrough. Richard found that in many applications a truncation level of 4 moves seem to work quite well. There is a paper by him on this topic in the proceedings of the conference Advances in Computer Games 2015 (in Leiden , NL), published by Springer Lecture Notes in Computer Science (LNCS). A very early application of truncated rollouts was applied by Brian Sheppard in his bot for Scrabble (MAVEN). Ingo. _______________________________________________ Computer-go mailing list [email protected] http://computer-go.org/mailman/listinfo/computer-go _______________________________________________ Computer-go mailing list [email protected] http://computer-go.org/mailman/listinfo/computer-go
