Home // International Journal On Advances in Intelligent Systems, volume 8, numbers 3 and 4, 2015 // View article

Human-Machine Cooperation Loop in Game Playing

Authors:
Maciej Świechowski
Kathryn Merrick
Jacek Mańdziuk
Hussein Abbass

Keywords: human-machine cooperation; human learning, game playing; UCT algorithm

Abstract:
This paper presents a new concept for human-machine iterative cooperation based on the Upper Confidence Bounds Applied to Trees method. Analysis of such human-computer cooperation may potentially lead to pertinent insights related to performance improvement of both the human subject and an artificial agent (machine) during certain kinds of strategic interactions. While the experiments described in this paper refer to the so-called General Game Playing (being a certain embodiment of multi-game playing) the overall idea of proposed human-machine cooperation loop extends beyond game domain and can, in principle, be implemented in the form of a flexible general-purpose system applicable to cooperative problem solving or strategic interactions of various kinds. The concept proposed in this study is evaluated by means of a direct involvement of human subjects in specifically defined cooperative environment, which provides vast opportunity to learn from and cooperate with an artificial game playing agent under the certain rules of cooperation. The choice of games is seemingly important to this kind of experiment. Although the participants played better with the assistance of the machine in some of the games, they lost the track in subsequent matches when the assistance was (intentionally) no longer available. Possible reasons for such an activity pattern are discussed in the conclusions. Three design iterations showing evolution of the experiment setup are presented in the paper. The analysis of cooperative and non-cooperative matches reveals different patterns for each chosen game characterized by various levels of advantage gained by means of cooperation.

Pages: 310 to 323

Copyright: Copyright (c) to authors, 2015. Used with permission.

Publication date: December 30, 2015

Published in: journal

ISSN: 1942-2679