Game-AI Forum

Thanks Alvaro for the nice summary. Their results are indeed mind boggling. When I first heard of CNNs a year or so ago,
I thought they were just yet another way of improving the move selection phase of MCTS...

Perft (partial game tree size) estimation can be a good testbed for MCTS experiments. https://dl.dropboxusercontent.com/u/55295461/perft/perft.pdf Abstract Partial game tree sizes can be estimated using different methods among which the most accurate is conducting monte-carlo simulations of random g...