Publication - Communication in Multi-agent Markov Decision Processes

Authors: Xuan, Ping, Lesser, Victor, Zilberstein, Shlomo
Title: Communication in Multi-agent Markov Decision Processes
Abstract: In this paper, we formulate agentís decision process under the framework of Markov decision processes, and particular, the multi-agent extension to Markov decision process that includes agent communication decisions. We model communication as the way for each agent to obtain local state information in other agents, by paying a certain communication cost. Thus, agents have to decide not only which local action to perform, but also whether it is worthwhile to perform a communication action before deciding the local action. We believe that this would provide a foundation for formal study of coordination activities and may lead to some insights to the design of agent coordination policies, and heuristic approaches in particular. An example problem is studied under this framework and its implications to coordination are discussed.
Keywords: Coordination, Distributed MDP, Multi-Agent Systems
Publication: Proceedings of the Fourth International Conference on MultiAgent Systems (ICMAS-00), Poster Session
Date: January 2000
Sources: PDF: /Documents/xuan00communication1.pdf
Reference: Xuan, Ping, Lesser, Victor, Zilberstein, Shlomo. Communication in Multi-agent Markov Decision Processes. Proceedings of the Fourth International Conference on MultiAgent Systems (ICMAS-00), Poster Session. January 2000.
bibtex:
@article{Xuan-202,
  author    = "Ping Xuan and Victor Lesser and Shlomo Zilberstein",
  title     = "{Communication in Multi-agent Markov Decision
               Processes}",
  journal   = "Proceedings of the Fourth International Conference
               on MultiAgent Systems (ICMAS-00), Poster Session",
  month     = "January",
  year      = "2000",
  url       = "http://mas.cs.umass.edu/paper/202",
}