Boosting material modeling using game tree search

Boosting Material Modeling Using Game Tree Search

Composition optimization of material is common and costly problem. To avoid redundant measurements, it is effective to expect unknown result by considering previous results. However, the expectation is frequently wrong due to unexpected characteristics inside real materials and it causes local optimum trap. This study presents game tree search can escape from local optimum by limiting the spati...

Phone duration modeling using gradient tree boosting

APHID Game-Tree Search

This paper introduces the APHID (Asynchronous Parallel Hierarchical Iterative Deepening) game-tree search algorithm. An APHID search is controlled by a master and a series of slave processors. The master searches the rst d 0 ply of the game-tree repeatedly. The slaves are responsible for the bottom plies of the game-tree. The slaves asynchronously read work lists from the master and return scor...

Bootstrapping from Game Tree Search

In this paper we introduce a new algorithm for updating the parameters of a heuristic evaluation function, by updating the heuristic towards the values computed by an alpha-beta search. Our algorithm differs from previous approaches to learning from search, such as Samuel’s checkers player and the TD-Leaf algorithm, in two key ways. First, we update all nodes in the search tree, rather than a s...

Multi-processor Game-tree Search

The design, implementation, and performance of two chess programs running on a multi-processor system are presented. Methods for distributing and enhancing the alpha-beta algorithm in a parallel environment are discussed. With the Principal Variation Splitting method, a four processor chess program yields a 3.35 fold speed-up over the sequential version. [Recreated from files dated 4 May 1984 i...