News for hackers. Stuff that matters.
Re:A way to deal with enormous branching factors in strategy... by shoyer on Friday March 25, 2016 @04:57PM (#11362635)
This seems like a less sophisticated variant* of the AlphaGo approach. In both cases, Monte Carlo Tree Search (MCTS) is constrained by model for likely future moves. Here, they use a genetic algorithm. In AlphaGo, this is called the "policy network".

* This is not to say that these authors copied AlphaGo -- my uninformed guess is that this general approach of constraining MCTS has been known for a very long time.

Re:A way to deal with enormous branching factors in strategy... by jebediah on Friday March 25, 2016 @05:19PM (#11362753)
If I understood correctly, they are not using any MCTS, I believe they are not doing any look ahead, only greedily selecting the best turn.
Re:A way to deal with enormous branching factors in strategy... by togelius on Saturday March 26, 2016 @12:32AM (#11364438)
Correct - we are not using MCTS and the approach has nothing to do with AlphaGo.