A new training paradigm, caned the "eomparison pa.radigm," is introduced for tasks in which a. network must learn to choose a prdcrred pattern from a set of n alternatives, based on examplcs of Imma.n expert prderences. In this pa.radigm, the inpu t to the network consists of t.wo uf the n alterna tives, and the trained output is the expert's judgement of which pa.ttern is better. This para.digm is applied to the lea,rning of hackgammon, a difficult board ga.me in wllieh the expert selects a move from a. set, of legal mm·es. Furthermorf', it is possible to set up the network so tha.t it always produces consisten t rank-orderings .

Many events such as flight delays or the absence of a member require the crew pool rescheduling team to change the initial schedule (rescheduling). In this paper, we show that the neural network comparison paradigm applied to the backgammon game by Tesauro (Tesauro and Se(cid:173) jnowski, 1989) can also be applied to the rescheduling problem of an aircrew pool. Indeed both problems correspond to choosing the best solut.ion The paper explains from a math(cid:173) ematical point of view the architecture and the learning strategy of the backpropagation neural network used for the best choice prob(cid:173) lem. We also show how the learning phase of the network can be accelerated.

This paper presents a new method, Minimax Tree Optimization (MMTO), to learn a heuristic evaluation function of a practical alpha-beta search program. The evaluation function may be a linear or non-linear combination of weighted features, and the weights are the parameters to be optimized. To control the search results so that the move decisions agree with the game records of human experts, a well-modeled objective function to be minimized is designed. Moreover, a numerical iterative method is used to nd local minima of the objective function, and more than forty million parameters are adjusted by using a small number of hyper parameters. This method was applied to shogi, a major variant of chess in which the evaluation function must handle a larger state space than in chess. Experimental results show that the large-scale optimization of the evaluation function improves the playing strength of shogi programs, and the new method performs signicantly better than other methods. Implementation of the new method in our shogi program Bonanza made substantial contributions to the program's rst-place nish in the 2013 World Computer Shogi Championship. Additionally, we present preliminary evidence of broader applicability of our method to other two-player games such as chess.

Many events such as flight delays or the absence of a member require the crew pool rescheduling team to change the initial schedule (rescheduling). In this paper, we show that the neural network comparison paradigm applied to the backgammon game by Tesauro (Tesauro and Sejnowski, 1989)can also be applied to the rescheduling problem of an aircrew pool. Indeed both problems correspond to choosing the best solut.ion

Many events such as flight delays or the absence of a member require the crew pool rescheduling team to change the initial schedule (rescheduling). In this paper, we show that the neural network comparison paradigm applied to the backgammon game by Tesauro (Tesauro and Sejnowski, 1989) can also be applied to the rescheduling problem of an aircrew pool. Indeed both problems correspond to choosing the best solut.ion

Many events such as flight delays or the absence of a member require the crew pool rescheduling team to change the initial schedule (rescheduling). In this paper, we show that the neural network comparison paradigm applied to the backgammon game by Tesauro (Tesauro and Sejnowski, 1989) can also be applied to the rescheduling problem of an aircrew pool. Indeed both problems correspond to choosing the best solut.ion

In this pa per, 'vc considcr problem domains in which tlte expert is givcn a s('t of 71.

A new training paradigm, caned the "eomparison pa.radigm," is introduced for tasks in which a. network must learn to choose a prdcrred pattern from a set of n alternatives, based on examplcs of Imma.n expert prderences. In this pa.radigm, the inpu t to the network consists of t.wo uf the n alterna tives, and the trained output is the expert's judgement of which pa.ttern is better. This para.digm is applied to the lea,rning of hackgammon, a difficult board ga.me in wllieh the expert selects a move from a. set, of legal mm·es.

A new training paradigm, caned the "eomparison pa.radigm," is introduced for tasks in which a. network must learn to choose a prdcrred pattern from a set of n alternatives, based on examplcs of Imma.n expert prderences. In this pa.radigm, the inpu t to the network consists of t.wo uf the n alterna tives, and the trained output is the expert's judgement of which pa.ttern is better. This para.digm is applied to the lea,rning of hackgammon, a difficult board ga.me in wllieh the expert selects a move from a. set, of legal mm·es.