2017-11-16 17:37 UTC+01:00, Gian-Carlo Pascutto <g...@sjeng.org>: > Third, evaluating with a different rotation effectively forms an > ensemble that improves the estimate.
Could you expand on that? I understand rotating the board has an impact for a neural network, but how does that change anything for a tree search? Or is it because the monte carlo tree search relies on the policy network? > As for a theoretical viewpoint: the value net is an estimation of the > value of some fixed amount of Monte Carlo rollouts. Could it be possible to train a value net using only the results of already finished games, rather than monte carlo rollouts? What about the value network from [Multi-Labelled Value Networks for Computer Go https://arxiv.org/abs/1705.10701 ], which can compute an estimate of the score by assigning each intersection of the board a probability that it will be black territory? (It does compute a more usual winrate estimation, but it also computes a territory estimation). >> What would you say is the current state-of-art game tree search for >> chess? That's a very unfamiliar world for me, to be honest all I >> really know is MCTS... > > The same it was 20 year ago, alpha-beta. Though one could certainly make > the argument that an alpha-beta searcher using late move reductions > (searching everything but the best moves less deeply) is searching a > tree of a very similar shape as an UCT searcher with a small exploration > constant. My (extremely vague and possibly fallacious) understanding of the situation was that monte carlo tree search was less effective for chess because of the more sudden changes there might be when evaluating chess positions. For instance, a player with an apparently lesser position might actually be a few moves away from a checkmate (or just from a big gain), which might be missed by the monte carlo tree search because it depends on one particular branch of the tree. _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
