A CHESS-PLAYING COMPUTER PROGRAM

ICGA Journal

2011

The article describes a model of chess based on information theory. A mathematical model of the partial depth scheme is outlined and a formula for the partial depth added for each ply is calculated from the principles of the model. An implementation of alpha-beta with partial depth is given. The method is tested using an experimental strategy having as objective to show the effect of allocation of a higher amount of search resources on areas of the search tree with higher information. The search proceeds in the direction of lines with higher information gain. The effects on search performance of allocating higher search resources on lines with higher information gain are tested experimentaly and conclusive results are obtained. In order to isolate the effects of the partial depth scheme no other heuristic is used.

INFOR: Information Systems and Operational Research, 1973

The purpose of this paper is to discuss ideas used in current chess playing programs. A short history of events leading to the present state of the art is given and a survey made of present day programs. The Newell, Shaw, and Simon program of 1958 is included since it embodies useful ideas that other programs appear not to employ. The possible performance limits for current techniques will be considered, including reasons for these beliefs. A summary of the major ideas contained in these programs is then presented and suggestions made for the improvement and development of future chess-playing programs. RESUME Le but de cet article est de discuter certaines iddes utilisdes dans les programmes pour le jeu d'echecs. On pr&ente un bref historique des ^vfenements qui ont abouti a l'dtat actuel. On fait la revue des programmes actuels. Le programme de Newell, Shaw, et Simon, ^crit en 1958, est inclus. En effet, il incorpore certaines id^es utiles qui ne semblent pas Stre encore exploit^es dans les programmes actuels. Les limitations des mdthodes courantes ainsi que leurs causes sont considdr^es. Finalement, on resume les id^es principales contenues dans ces programmes et on pr^sente des suggestions pour l'am^lioration et le d^veloppement des programmes qui jouent aux dchecs.

International Journal of Engineering, 2015

This paper describes a system for automated chess playing with a robot manipulator. Customized chess engine is used to implement chess rules, to evaluate the board position during the game and to compute the next move of the robot using the alpha-beta search algorithm. This work contributes to the recent trends for creating automated robotic games and introduction of non-standard human-computer interfaces.

2000

Article prepared for the ENCYCLOPEDIAOF ARTIFICIAL INTELLIGENCE, S. Shapiro (editor), D. Eckroth (Managing Editor) to be published by John Wiley, 1987.

Arxiv preprint arXiv: …, 2010

In this paper we introduce a novel method for automatically tuning the search parameters of a chess program using genetic algorithms. Our results show that a large set of parameter values can be learned automatically, such that the resulting performance is comparable with that of manually tuned parameters of top tournament-playing chess programs.

Computational Intelligence, 1996

This paper introduces METAGAMER, the first program designed within the paradigm of Metagame-playing (Metagame). This program plays games in the class of symmetric chess-like games, which includes chess, Chinese chess, checkers, draughts, and Shogi. METAGAMER takes as input the rules of a specific game and analyzes those rules to construct an efficient representation and an evaluation function for that game; they are used by a generic search engine. The strategic analysis performed by METAGAMER relates a set of general knowledge sources to the details of the particular game. Among other properties, this analysis determines the relative value of the different pieces in a given game. Although METAGAMER does not learn from experience, the values resulting from its analysis are qualitatively similar to values used by experts on known games and are sufficient to produce competitive performance the first time METAGAMER plays a new game. Besides being the first Metagame-playing program, this is the first program to have derived useful piece values directly from analysis of the rules of different games. This paper describes the knowledge implemented in METAGAMER, illustrates the piece values ME?AGAMER derives for chess and checkers, and discusses experiments with METAGAMER on both existing and newly generated games.

Abstract: This paper aims at throwing light on the new mode of playing board games by having an automated physical platform. Hence it discusses the development of an automatic chess board called as Chess.Automated. which enables the user to play the game of chess in different formats; with the opponents moves completely automated. It uses various electronic components such as the Arduino Mega2560 Microcontroller, Membrane Keypad and driver IC’s along with different programming languages such C++, Python and Java to achieve automation between software and hardware. Keywords: Arduino Mega2560, Chess.Automated, Online gameplay, Membrane keypad, MRL (My Robot Lab).

Autonomous Chess Playing Robot is a robot that can challenge a human's chess playing ability in a tangible environment with its varying difficulty level. As any other autonomous robot, ACPR is based upon three pillars, viz. electronics, programming, and mechanical design. The robot consists of a customized chess board below which LDR sensors have been fabricated on a PCB (Printed Circuit Board). Multiplexers also being laid on PCB provide a way for one-way serial communication between sensors and microcontroller. Linear sliders facilitate horizontal and vertical movement of the gripper to move a piece from one position to other. The linear sliders use rack and pinion mechanism while the gripper uses the concept of four bar linkage mechanism. The crucial element of the robot i.e. the intelligence has been incorporated with the help of MinMax algorithm supported by alpha-beta pruning. The microcontroller is connected to a computer terminal by a USB and the chess engine code runs on the computer terminal itself.

Game playing in chess is one of the important areas of machine learning research. Though creating a powerful chess engine that can play at a superhuman level is not the hardest problem anymore with the advent of powerful chess engines like Stockfish, Alpha Zero, Leela chess zero etc. Most of these engines still depend upon powerful and highly optimized look-ahead algorithms. CNN(convolutional neural networks) which is used primarily for images and matrix-like data is been proved successful with games like chess and go. In this project, we are treating chess like a regression problem. In this paper, we have proposed a supervised learning approach using the convolutional neural network with a limited look ahead. We have collected data of around 44029 chess games from the FICS chess database with players having an Elo rating of 2000 and above. Our goal is to create a zero-knowledge chess engine. The trained model is then paired with a minimax algorithm to create the AI. Our proposed supervised system can learn the chess rules by itself from the data. It was able to win 10% of the games and draw 30% of games when manually tested against Stockfish computer engine with Elo of 1300. We suggest that CNN can detect various tactical pattern to excel in games like chess even when using a limited lookahead search.

2021

Game playing in chess is one of the important areas of machine learning research. Though creating a powerful chess engine that can play at a superhuman level is not the hardest problem anymore with the advent of powerful chess engines like Stockfish, Alpha Zero, Leela chess zero etc. Most of these engines still depend upon powerful and highly optimized look-ahead algorithms. CNN(convolutional neural networks) which is used primarily for images and matrix-like data is been proved successful with games like chess and go. In this project, we are treating chess like a regression problem. In this paper, we have proposed a supervised learning approach using the convolutional neural network with a limited look ahead. We have collected data of around 44029 chess games from the FICS chess database with players having an Elo rating of 2000 and above. Our goal is to create a zero-knowledge chess engine. The trained model is then paired with a minimax algorithm to create the AI. Our proposed supervised system can learn the chess rules by itself from the data. It was able to win 10% of the games and draw 30% of games when manually tested against Stockfish computer engine with Elo of 1300. We suggest that CNN can detect various tactical pattern to excel in games like chess even when using a limited lookahead search.

IRJET, 2021

Game playing in chess is one of the important areas of machine learning research. Though creating a powerful chess engine that can play at a superhuman level is not the hardest problem anymore with the advent of powerful chess engines like Stockfish, Alpha Zero, Leela chess zero etc. Most of these engines still depend upon powerful and highly optimized look-ahead algorithms. CNN(convolutional neural networks) which is used primarily for images and matrix-like data is been proved successful with games like chess and go. In this project, we are treating chess like a regression problem. In this paper, we have proposed a supervised learning approach using the convolutional neural network with a limited look ahead. We have collected data of around 44029 chess games from the FICS chess database with players having an Elo rating of 2000 and above. Our goal is to create a zero-knowledge chess engine. The trained model is then paired with a minimax algorithm to create the AI. Our proposed supervised system can learn the chess rules by itself from the data. It was able to win 10% of the games and draw 30% of games when manually tested against Stockfish computer engine with Elo of 1300. We suggest that CNN can detect various tactical pattern to excel in games like chess even when using a limited lookahead search.

Lecture Notes in Computer Science, 1995

Current computer-chess programs achieve outstanding results in chess playing. However, there is a deficiency of evaluative comments on chess positions. In this paper, we propose a case-based model that supplies a comprehensive positional analysis for any given position. This analysis contains evaluative comments for the most significant basic features found in the position and a general evaluation for the entire position. The analysis of the entire position is presented by an appropriate Multiple eXplanation Pattern (MXP), while the analysis of each chosen feature is presented by a suitable eXplanation Pattern (XP). The proposed analysis can improve weak and intermediate players' play in general and their understanding, evaluating and planning abilities in particular. This model is part of an intelligent educational chess system which is under development. At present, our model deals only with a static evaluation of chess positions; addition of searching and playing modules remains for future work.

The game of chess has sometimes been referred to as the Drosophila of artificial intelligence and cognitive science research --a standard task that serves as a test bed for ideas about the nature of intelligence and computational schemes for intelligent systems. Both machine intelligence --how to program a computer to play good chess (artificial intelligence) -and human intelligence --how to understand the processes that human masters use to play good chess (cognitive science) --are encompassed in the research, and we will comment on both in this chapter, but with emphasis on computers.

ICGA Journal, 1993

We describe a suite of 5500 test positions for testing chess playing programs. They are available as pub/wds/ChessTest.tar.Z by anonymous ftp to external.NJ.NEC.COM. Almost all of these positions are unoriginal and were obtained by scanning in diagrams from chessbooks with an optical scanner. Gnuchess 4.0, at one minute per move on a 50 MHz MIPS R4000, scores 16-71% on our test les. We describe the software we wrote to accomplish the scanning task. If you take the test, please send us