A comparison of agent decommitment techniques in a real-time environment

  • Authors:

  • Michele Van Dyne;Costas Tsatsoulis

  • Affiliations:

  • Computer Science Department, Montana Tech of the University of Montana, Butte, MT;Department of Computer Science and Engineering, University of North Texas, Denton, Texas

  • Venue:
  • AIKED'10 Proceedings of the 9th WSEAS international conference on Artificial intelligence, knowledge engineering and data bases
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Decommitment of agents has been studied in the context of self-interested agent societies, primarily using a leveled commitment protocol in which agents committing a breach of contract are penalized in various ways. Limited research has investigated decommitment in collaborative agent populations. This research investigates decommitment in a collaborative agent society, in which agents make decisions and act in a manner which maximizes the global benefit. In this environment, decommitment takes on a different nuance, in that collaborative agent behavior can be expected not to cause harm to the agent society as a whole, even in decisions not to honor prior commitments. The operating environment in this study is both timebounded and resource constrained. This research studies three levels of agent decommitment: 1) no decommitment, 2) unilateral decommitment, and 3) negotiated decommitment. Results indicate that negotiated decommitment generally performed as hypothesized, that is, overall performance was significantly improved over the baseline condition, and, with certain criteria, its performance was significantly improved over the unilateral decommitment condition.