Section 4 : Recent game programs

Commentary

Section Goals

• To briefly present state-of-the-art game programs.
• To introduce some of the more recent game programs.

Learning Objectives

Learning Objective 1

• Name the most recently advanced application of AI in game programs.
• Summarize the progress of game programs in recent years, and describe in detail the one that most interests you.

Objective Readings

Required Readings

State-of-the-Art Game Programs (see Section 5.7 - 5.8 of AIMA3ed)

Selected papers from: -- (2002). Artificial Intelligence, 134(1-2), 1-318.

• Schaeffer, J., and van den Herik, H. J. (2002). Games, computers, and artificial intelligence. Artificial Intelligence, 134(1-2), 1-7.
• Korf, R.E., and Felner, A. (2002). Disjoint pattern database heuristics. Artificial Intelligence, 134(1-2), 9-22.
• Littman, M. L., Keim, G. A., and Shazeer, N. (2002). A probabilistic approach to solving crossword puzzles. Artificial Intelligence, 134(1-2), 23-55.
• Campbell, M., Hoane A. J. Jr., and Hsu, F.-H. (2002). Deep Blue. Artificial Intelligence, 134(1-2), 57-83.
• Buro, M. (2002). Improving heuristic mini-max search by supervised learning. Artificial Intelligence, 134(1-2), 85-99.
• Anshelevich, V. V. (2002). A hierarchical approach to computer Hex. Artificial Intelligence, 134(1-2), 101-120.
• Iida, H., Sakuta, M., and Rollaso, J. (2002). Computer shogi. Artificial Intelligence, 134(1-2), 121-144.
• Müller, M. (2002). Computer Go. Artificial Intelligence, 134(1-2), 145-179.
• Tesauro, G. (2002). Programming backgammon using self-teaching neural nets. Artificial Intelligence, 134(1-2), 181-199.
• Billings, D., Davidson, A., Schaeffer, J., and Szafron, D. (2002). The challenge of poker. Artificial Intelligence, 134(1-2), 201-240.
• Sheppard, B. (2002). World-championship-caliber Scrabble. Artificial Intelligence, 134(1-2), 241-275.
• van den Herik, H. J., Uiterwijk, J. W. H. M., and van Rijswijck, J. (2002). Games solved: Now and in the future. Artificial Intelligence, 134(1-2), 277-311.

Objective Questions

• What is the main problem in game programs, and which search technology is the most important one to handle the problem?
• In your opinion, which game program is the most successful, and the most comparable to a human being?
• What is your vision of AI-based game programs in the near future, say in ten or twenty years?

Objective Activities

• Discuss the questions above in the online course conference, and share your vision with the other graduate students.
• Explore some open source or freely downloadable game programs from the Internet, and play them on your computer. Determine how you could improve the performance of these games using the most recent AI technology. Share your experiences with others through the course conference.