MoHex 2.0: A Pattern-Based MCTS Hex Player
نویسندگان
چکیده
In recent years the Monte Carlo tree search revolution has spread from computer Go to many areas, including computer Hex. MCTS Hex players now outperform traditional knowledge-based alpha-beta search players, and the reigning Computer Olympiad Hex gold medallist is the MCTS player MoHex. In this paper we show how to strengthen MoHex, and observe that — as in computer Go — using learned patterns in priors and replacing a hand-crafted simulation policy with a softmax policy that uses learned patterns can significantly increase playing strength. The result is MoHex 2.0, about 250 Elo stronger than MoHex on the 11×11 board, and 300 Elo stronger on 13×13.
منابع مشابه
Move Prediction using Deep Convolutional Neural Networks in Hex
Using deep convolutional neural networks for move prediction has led to massive progress in Computer Go. Like Go, Hex has a large branching factor that limits the success of shallow and selective search. We show that deep convolutional neural networks can be used to produce reliable move evaluation in the game of Hex. We begin by collecting self-play games of MoHex 2.0. We then train the neural...
متن کاملHex 2017: MoHex wins the 11x11 and 13x13 tournaments
The 2017 Olympiad in Leiden hosted two Hex tournaments, board sizes 11×11 and 13×13. Three programs competed in each tournament. These are at present the only annual computer Hex tournaments. 11×11 is the original board size introduced by Piet Hein in 1942. Recently, all 1-move openings on 9×9Hex have been solved by computers, as have two 10×10 openings [9]. So, in recent years the 13×13 compet...
متن کاملSibling Conspiracy Number Search
For some two-player games (e.g. Go), no accurate and inexpensive heuristic is known for evaluating leaves of a search tree. For other games (e.g. chess), a heuristic is known (sum of piece values). For other games (e.g. Hex), only a local heuristic — one that compares children reliably, but nonsiblings poorly — is known (cell voltage drop in the Shannon/Anshelevich electric circuit model). In t...
متن کاملConspiracy number search with relative sibling scores
For some two-player games (e.g. Go), no accurate and inexpensive heuristic is known for evaluating leaves of a search tree. For other games (e.g. chess), a heuristic is known (sum of piece values). For other games (e.g. Hex), only a local heuristic — one that compares children reliably, but non-siblings poorly — is known (cell voltage drop in the Shannon/Anshelevich electric circuit model). In ...
متن کاملMonte-Carlo Tree Search for Poly-Y
Monte-Carlo tree search (MCTS) is a heuristic search algorithm that has recently been very successful in the games of Go and Hex. In this paper, we describe an MCTS player for the game of Poly-Y, which is a connection game similar to Hex. Our player won the CodeCup 2014 AI programming competition. Our player uses MCTS with the all-moves-as-first heuristic, and detects basic heuristic patterns t...
متن کامل