1

I'm programming on Connect6 with MCTS.

Monte Carlo Tree Search is based on random moves. It counts up the number of wins in certain moves. (Whether it wins with 3 turns or 30 turns)

Is the move with less turns more powerful than the move with more turns? And if so, is it meaningful to give bigger weight to the one with less turn win?

kim
  • 11
  • 1
  • If I understand you correctly, I think an idea similar to yours is described in the following paper which you may want to read: https://dke.maastrichtuniversity.nl/m.winands/documents/QB_ECAI2014.pdf . Apart from that, I think this question is off-topic on this particular site since it's not directly about programming/implementation. The question would be more suitable to ask on https://ai.stackexchange.com/ instead. If you decide to ask it there, it may also be useful to elaborate a bit more, the question is not 100% clear. – Dennis Soemers Oct 07 '18 at 16:40
  • So pleased with your kind remark. I'm sure you understood my question perfectly. I'll definitely read the file you have linked and ask this question once more on ai.stackexchange.com ! Thank u :D – kim Oct 07 '18 at 17:33

0 Answers0