We used neural networks (learnt by DirectPolicySearch) for making MCTS compliant with problems with long horizons. But this was not for the game of Go. http://hal.inria.fr/hal-00759822/
MCTS has a problem for long horizons, and a Direct Policy Search with neural networks is a solution for learning a default playout. Best regards, Olivier 2013/5/2 Steven Clark <[email protected]> > Hello all- > > Has anyone successfully used neural nets to help guide MC playouts? > Has anyone used NN to learn patterns larger than 3x3? > > I'm working on a grad-school project, and discovered a few interesting > things. > After analyzing 10,000+ high-dan games from KGS, I find that more than 50% > of the time, moves are played within a 5x5 window centered at the > opponent's previous move (call this a "tactical" move, vs a strategic move). > > I used the FANN library to learn these 5x5 patterns, and found that the NN > could predict tactical moves with ~27% accuracy (and with a >50% chance > that the answer would be in the top 3 moves proposed by the NN). > > Is this old news? Are neural nets just too slow to be helpful to MC > (reduce the playout rate too much?) > > Thoughts welcome. I will be up late finishing the report since it is due > tomorrow ;) > > -Steven > > _______________________________________________ > Computer-go mailing list > [email protected] > http://dvandva.org/cgi-bin/mailman/listinfo/computer-go > -- ========================================================= Olivier Teytaud, [email protected], TAO, LRI, UMR 8623(CNRS - Univ. Paris-Sud), bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France http://www.slideshare.net/teytaud -- ========================================================= Olivier Teytaud, [email protected], TAO, LRI, UMR 8623(CNRS - Univ. Paris-Sud), bat 490 Univ. Paris-Sud F-91405 Orsay Cedex France http://www.slideshare.net/teytaud
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
