One Jump Ahead: Challenging Human Supremacy in Checkers

نویسنده

  • Jonathan Schaeffer
چکیده

University of Alberta set out to build a world checkers champion. He succeeded. In 1994, CHINOOK, the program written by Schaeffer and his group, won the Man versus Machine World Checkers Championship. (Although CHINOOK has now mostly retired from championship checkers, it is still possible to play CHINOOK. To play CHINOOK or just see information about CHINOOK and checkers in general, go to www.cs.ualberta.ca/~chinook.) Schaeffer then went on to write a book about his quest. The result, One Jump Ahead: Challenging Human Supremacy in Checkers, is an extraordinary book. One Jump Ahead provides a history of CHINOOK, from its initial success in winning the United States Checkers Championship in 1990 through its losses to the world human checkers champion to its eventual success. By the way, Schaeffer gives an excellent talk about his experiences with CHINOOK that I also highly recommend. If One Jump Ahead had merely been a chronicle of the technical achievements in the development of CHINOOK, it would have been a good book. However, the book is instead more about the human aspects of Schaeffer’s journey from checkers neophyte to friend of many of the world’s best human checkers players. The last book that I read that was anything like One Jump Ahead was Tracy Kidder’s book, The Soul of a New Machine (Little, Brown, and Company, 1981). However, One Jump Ahead is quite different and, in my opinion, much better. The Soul of a New Machine was written by an outsider— one who was not really part of the activities involved in the building of a new microprocessor. Nevertheless, it pro-

برای دانلود 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

Any reason for using Computational Intelligence methods in classical mind board games?

In the last two decades the advancement of AI/CI methods in classical board and card games (such as Chess, Checkers, Othello, Go, Poker, Bridge, ...) has been enormous. In nearly all “world famous” games the humans have been decisively conquered by the machines (actually Go remains almost the last redoubt of human supremacy). In the above perspective the natural question that comes to our minds...

متن کامل

Learning in Repeated Games: Human Versus Machine

While Artificial Intelligence has successfully outperformed humans in complex combinatorial games (such as chess and checkers), humans have retained their supremacy in social interactions that require intuition and adaptation, such as cooperation and coordination games. Despite significant advances in learning algorithms, most algorithms adapt at times scales which are not relevant for interact...

متن کامل

Solving Checkers

AI has had notable success in building highperformance game-playing programs to compete against the best human players. However, the availability of fast and plentiful machines with large memories and disks creates the possibility of a game. This has been done before for simple or relatively small games. In this paper, we present new ideas and algorithms for solving the game of checkers. Checke...

متن کامل

The role of the Triple islands (Greater Tunb, Lesser Tunb and Abu Musa) in Iran’s Maritime supremacy in the Persian Gulf

For many coastal countries, maritime supremacy has always been a major concern of their grand strategies. The existence of islands is one of the most important means to acquisition of maritime supremacy in maritime territories. Iran, Due to its maritime position, has many islands in the Persian Gulf, the most important of which are the Triple  islands (Greater Tunb, Lesser Tunb and Abu Musa). T...

متن کامل

Multi-Step-Ahead Prediction of Stock Price Using a New Architecture of Neural Networks

Modelling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network (ANN) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of di...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1997