An Evaluation Function for Shogi

نویسنده

  • Reijer Grimbergen
چکیده

Shogi and chess are similar games. The aim in both games is to mate the opponent's king. However, the main di erence between shogi and chess is that in shogi pieces taken from the opponent can be used again. This has important consequences for the evaluation function. In chess the material balance is vital for the evaluation of a position while in shogi the evaluation of a position is much more based on abstract concepts like bad piece formations and danger to the king. In this paper a set of features will be proposed that are vital for an evaluation function for shogi. These features have been implemented in an evaluation function which is part of a complete shogi playing program. This evaluation function has been tested by comparing its position assessment with the opinion of professional players in 54 middlegame positions and 46 endgame positions from professional games. The evaluation function agreed with the expert opinion in 64 of these positions, judging the middlegame positions a little better (67%) than the endgame position (61%).

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Using Pattern Recognition and Selective Deepening to Solve Tsume Shogi

In chess brute-force search methods have been very successful. However, games like shogi have a game tree complexity that is much higher than chess. Therefore, it is unclear if the methods used for making strong chess programs will also be successful for other games. In our research we will attempt to use a more cognitively based method, pattern recognition, to build a strong shogi playing prog...

متن کامل

Large-Scale Optimization for Evaluation Functions with Minimax Search

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 w...

متن کامل

Computer shogi

This paper describes the current state of the art in computer shogi. Shogi (Japanese chess) promises to be a good vehicle for future research into game-playing programs that are based on tree-searching paradigms. This paper shows where chess and shogi are similar, and details the important areas that make shogi programming of particular interest. A crucial difference is the game-tree complexity...

متن کامل

A Randomized Game-Tree Search Algorithm for Shogi Based on Bayesian Approach

We propose a new randomized game-tree search algorithm based on Bayesian Approach. It consists of two main concepts; (1) using multiple game-tree search with a randomized evaluation function as simulations, (2) treating evaluated values as probability distribution and propagating it through the game-tree using the Bayesian Approach concept. Proposed method is focusing on applying to tactical ga...

متن کامل

An FPGA-based processor for shogi mating problems

After the success of DEEP BLUE in computer chess, shogi, or Japanese chess is a next challenging target in artificial intelligence for game playing. The complexity and huge search space of shogi have been motivating researchers to make shogi programs, but none of them is competent enough to play against human experts. To improve competence of shogi programs, it is a promising approach to develo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007