Summary
Robbi is an ER 56 computer programmed to play a simple nXn (2≦n≦9) board game against human opponents or against itself, that is, to play both sides of the game. Of special interest in the playing program is the learning routine, which improves the performance of the system as it gains experience with the actual game. The efficiency of the machine-learning procedure combined with various tactics adopted by the players has been studied in some detail. The results of each run are tabulated, i.e. the number of plays and the machine-playing time necessary to achieve the criteria of learning, the number of losses, the number of corrections, and the number of board positions stored in the memory of the computer during a run together with their associated lists of possible alternatives, the number of which is reduced by those which have been proved to be incorrect responses. Both the efficiency of the learning system and the characteristic form of the learning curves depends on the combination of tactics used by the players.
Similar content being viewed by others
Literatur
Feigenbaum, E. A., and J. Feldman: Computers and thought. New York: McGraw-Hill Book Co. 1963.
Foppa, K.: Lernen, Gedächtnis, Verhalten. Köln: Kiepenheuer & Witsch 1965.
Gardner, M.: Sci. Amer. 206, 138–144 (March) (1962).
Luce, R. D., and H. Raiffa: Games and decisions. New York: John Wiley & Sons 1958.
Minsky, M.: A selected descriptor-indexed bibliography to the literature on artifical intelligence. IRE Transactions on Human Factors in Electronics, HFE-2: 39–55, March (1961).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pohley, H.J., Köhne, K. & Singer, A. Über das Lernverhalten des Automaten Robbi. Kybernetik 3, 226–238 (1967). https://doi.org/10.1007/BF00288552
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00288552