TOOLBOXBROWSE TOPICS
RESOURCESABOUT THIS SITEpmwiki.org |
More Games & Puzzles(a subtopic of Games & Puzzles) Matching (Chess) Wits. By Robert L. Smith. The Plain Dealer Sunday Magazine (January 5, 2003). "When IBM's chess-playing computer Deep Blue defeated Gary Kasparov in 1997, a pall fell over the chess world. It was clear that computers had come to dominate the game of chess. Omar Syed, a Lakewood computer engineer, took the news harder than most. Not only is he a chess fan, he's a student of artificial intelligence, holding advanced degrees in neural networks and genetic algorithms from Case Western Reserve University. Syed was willing to concede that computers make better chess players, but he does not believe that machines are smarter than humans. Not yet. To prove his point, Syed built what he believes is the first game intentionally designed to be difficult for computers. ... [H]e is offering a reward of $10,000 to the first person who can design a program that enables a computer to beat a human in Arimaa match play. The offer stands until 2020...."
PC network solves game. By Chrissie Davies. Financial Times (September 5, 2002). "Computer scientists in the Netherlands have solved an ancient strategy game, called awari, using a network of 144 personal computers and a problem-solving procedure, or algorithm. The game, played in many countries but especially in Africa and the West Indies, involves capturing opponents' stones or 'seeds'. ... This is a landmark achievement in artificial intelligence and follows Deep Blue's success in beating chess champion Gary Kasparov in 1997."
Temporal Difference Learning and TD-Gammon. By Gerald Tesauro. Originally published in Communications of the ACM, March 1995 / Vol. 38, No. 3. "This article presents a game-learning program called TD-Gammon. TD-Gammon is a neural network that trains itself to be an evaluation function for the game of backgammon by playing against itself and learning from the outcome."
The technology behind backgammon - The die is cast as artificial intelligence takes online backgammon to a new level. By Paul Wardley. Personal Computer World (June 12, 2006). "Backgammon is the oldest known board game, with a history spanning thousands of years. ... Much of the renewed interest in the game stems from its connection with computing technology: not only because backgammon is being packaged as a hot new form of online gaming or because a PC is a tireless and always-available opponent, but because backgammon has become one of the success stories of research into artificial intelligence (AI). Self-taught backgammon-playing computer programs are so good that they have overturned many of the assumptions previously held about how the game should be played and which are the best moves, especially in the opening phases of the game. ... Backgammon-playing programs are entirely self taught using the technique of reinforcement learning, which is one of the most promising avenues of research into artificial intelligence. ... The mode of reinforcement learning that has been so successful in teaching computers to play backgammon is called temporal difference (TD) learning, which is based on the differences between temporally successive predictions. ... Gerald Tesauro, an IBM researcher, is responsible for pioneering TD techniques with backgammon. His program, TD-Gammon, was developed after abandoning experiments with a supervised learning program called Neurogammon, in which the good and bad moves were hard-coded." The Neural Net Backgammon Programs. From Jay Scott's Machine Learning in Games web site. Learning to Play Black Jack with Artificial Neural Networks. By Andrés Perez-Urbie, Logic Systems Laboratory, Swiss Federal Institute of Technology-Lausanne. "Blackjack or twenty-one is a card game where the player attempts to beat the dealer, by obtaining a sum of card values that is equal to or less than 21 so that his total is higher than the dealer's. The probabilistic nature of the game makes it an interesting testbed problem for learning algorithms, though the problem of learning a good playing strategy is not obvious. ... We have explored the use of blackjack as a test bed for learning strategies in neural networks, and specifically with reinforcement learning techniques."
Hex. From Vadim V. Anshelevich (Vanshel). Learn about the game and download Hexy, a computer program that will play Hex with you!
Ancient game gets new life. By Burt Lum. The Honolulu Advertiser (April 1, 2003). "I played checkers, chess and Chinese checkers as a child, but lately I have rediscovered the game of konane. The game is played much like checkers but instead of trying to remove all the opponent's game pieces, the winner of konane is the player who has the last move. ... The thought and strategy behind konane have inspired many computer science courses on the subject. Several college classes on artificial intelligence have studied konane."
Software learns when it pays to deceive. By Zeeya Merali. NewScientist.com news (May 30, 2007; from Issue 2606: page 32). "Now [Evan] Hurwitz and Tshilidzi Marwala, also at [University of the Witwatersrand in South Africa], have developed a virtual player that has taught itself to bluff at a card game called lerpa. Their artificial intelligence bot, named Aiden, is based on a neural network algorithm that usually forecasts stock market fluctuations. ... 'This demonstrates that computers can learn this peculiarly human behaviour,' says Philippe de Wilde, a computer scientist at Heriot-Watt University in Edinburgh, UK. 'They generate the strategy from play, which is a very human way of learning.'" Renju computer programs. From the Renju International Federation. "Renju is the professional variant of Go-Moku and uses more sophisticated rules. In renju the black player (the beginner of a game) is not allowed to make double-threes, double-fours or more than five in a row." Shogi.Net "Shogi is a Japanese board game played by two players. The object of the game is to capture the opponent's King. Shogi is played on a nine-by-nine board and each player has twenty pieces. Shogi is much like 'western' chess, but has some very interesting differences. One is that almost all pieces can promote to stronger pieces once they reach the opposite side of the board." You'll finds lots of information here including a collection of Shogi software. Computer shogi. By Hiroyukia Iida, Makotoa Sakuta, and Jeff Rollason. In Artificial Intelligence, January 2002 (Volume: 134, Issue: 1-2). Excerpt from the Abstract: "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." Computer Shogi Association (CSA).
 Do not pass Go. Computers can beat the world's best chess players but have yet to master other classic games like Go. By David Levy. The Guardian (October 24, 2002). "Ever since Garry Kasparov's sensational 1997 loss to the IBM chess monster Deep Blue, the chess world has thirsted for revenge. But the first opportunity ended in failure in Bahrain on Saturday, when Kasparov's former pupil and successor as World Champion, Vladimir Kramnik, could only draw an 8-game match against one of the world's leading chess engines, Fritz. But this was just the latest in a long series of human versus computer encounters that illustrate the inexorable march of artificial intelligence (AI). It's a story that began at a Dartmouth University conference in 1956, when several of the founding fathers of AI defined the goals of that infant science. One of them was to create a computer program that could defeat the world chess champion. Success would, those scientists believed, reach to the very core of human intellectual endeavour. By the early 1990s, due in no small part to the successes achieved in computer chess, the interest of the AI community had spread to many other games of skill, including backgammon, bridge, Go and Scrabble. Where exactly are we now in this fascinating struggle?" Related Web SitesThe University of Alberta GAMES Group. In addition to playing their Hex program (Queenbee) online, you can check out some of their other game projects such as Amazons, Awari, Lines of Action, RoShamBo, Sokoban, and Shogi. Related Pages |
