Comparison of cheating AIs At 1s thinking time: Minimax MCTS 1 0.84
Comparison of cheating AIs At 1s thinking time: Minimax MCTS 1 0.84 At 4s thinking time: Minimax MCTS 1 1.53
Date: Sun, 4 Mar 2012 21:04:39 +0800 From: Melvin Zhang To: P. I. Cowling Subject: Applying MCTS to make all AI decisions ... Our own internal comparison with the original minimax AI confirms that MCTS has better performance than minimax. I hope that our preliminary findings and implementation would be helpful to you and your team in further research in this area. Regards, Melvin
3. Iterate, iterate, iterate
Monte-Carlo Tree Search without cheating Issue 92: Reported by eolebigot, Nov 12, 2011 Would it be possible for Magarena to have a *non-cheating* Monte-Carlo Tree Search? I tend to avoid the cheating AI, because I prefer fair games, so an MCTS that does not cheat would be great! https://code.google.com/p/magarena/issues/detail?id=92
Monte-Carlo AI not fully parallel Issue 344: Reported by eolebigot, Apr 28, 2013 For the cheating Monte-Carlo AI, 2 cores are used (instead of 4 thanks to hyperthreading). While this may be normal, this is quite unusual. For the non-cheating Monte-Carlo AI, only 1 core is used. https://code.google.com/p/magarena/issues/detail?id=344
Comparison of honest AIs At 1s thinking time: Minimax MCTS 1 0.88 (0.84)
Comparison of honest AIs At 1s thinking time: Minimax MCTS 1 0.88 (0.84) At 4s thinking time: Minimax MCTS 1 1.71 (1.53)
Open problems MCTS makes bad plays when it is losing.
Open problems MCTS makes bad plays when it is losing. Reduce occurrence of games which are not fun.