Bibliography

[TR+95] Architectures for Agents that Track Other Agents in Multi-Agent Worlds

Tambe.atal95 (In proceedings)
Author(s)	Tambe, Milind and Rosenbloom, Paul S.
Title	« Architectures for Agents that Track Other Agents in Multi-Agent Worlds »
In	the 1995 Workshop on Agent Theories, Architectures, and Languages
Page(s)	156--170
Year	1995
Address	Montréal

Tambe.atal95 (In proceedings)

Author(s)

Tambe, Milind and Rosenbloom, Paul S.

Title

« Architectures for Agents that Track Other Agents in Multi-Agent Worlds »

the 1995 Workshop on Agent Theories, Architectures, and Languages

Page(s)

156--170

Year

1995

Address

Montréal

Abstract
In multi-agent environments, an intelligent agent often needs to interact with other individuals or groups of agents to achieve its goals. Agent tracking is one key capability required for intelligent interaction. It involves monitoring the observable actions of other agents and inferring their unobserved actions, plans, goals and behaviors. This article examines the implications of such an agent tracking capability for agent architectures. It specifially focuses on real-time and dynamic environments, where an intelligent agent is faced with the challenge of tracking the highly fleible mix of goal-driven and reactive behaviors of other agents, in real-time. The key implication is that an agent architecture needs to provide direct support for fleible and effiient reasoning about other agents' models. In this article, such support takes the form of an architectural capability to execute the other agent's models, enabling mental simulation of their behaviors. Other architectural requirements that follow include the capabilities for (pseudo-) simultaneous execution of multiple agent models, dynamic sharing and unsharing of multiple agent models and high bandwidth inter-model communication. We have implemented an agent architecture, an experimental variant of the Soar integrated architecture, that conforms to all of these requirements. Agents based on this architecture have been implemented to execute two different tasks in a real-time, dynamic, multi-agent domain. The article presents experimental results illustrating the agents' dynamic behavior.

Abstract

In multi-agent environments, an intelligent agent often needs to interact with other individuals or groups of agents to achieve its goals. Agent tracking is one key capability required for intelligent interaction. It involves monitoring the observable actions of other agents and inferring their unobserved actions, plans, goals and behaviors. This article examines the implications of such an agent tracking capability for agent architectures. It specifially focuses on real-time and dynamic environments, where an intelligent agent is faced with the challenge of tracking the highly fleible mix of goal-driven and reactive behaviors of other agents, in real-time. The key implication is that an agent architecture needs to provide direct support for fleible and effiient reasoning about other agents' models. In this article, such support takes the form of an architectural capability to execute the other agent's models, enabling mental simulation of their behaviors. Other architectural requirements that follow include the capabilities for (pseudo-) simultaneous execution of multiple agent models, dynamic sharing and unsharing of multiple agent models and high bandwidth inter-model communication. We have implemented an agent architecture, an experimental variant of the Soar integrated architecture, that conforms to all of these requirements. Agents based on this architecture have been implemented to execute two different tasks in a real-time, dynamic, multi-agent domain. The article presents experimental results illustrating the agents' dynamic behavior.

BibTeX code

@inproceedings{Tambe.atal95,
  author = {Tambe, Milind and Rosenbloom, Paul S.},
  booktitle = {the 1995 Workshop on Agent Theories, Architectures, and
               Languages},
  domains = {Multi-Agent Systems/Agent Architecture/Cognitive
             Architecture:Virtual Reality:Simulation:},
  title = {Architectures for Agents that Track Other Agents in Multi-Agent
           Worlds},
  address = {Montr{\'e}al},
  pages = {156--170},
  year = 1995,
}

Documents in the same domains

Root

Multi-Agent Systems/Agent Architecture/Cognitive Architecture

		[KB+99] Kline C. et al., "The Art and Science of Synthetic..." (1999)
		[Nag02] Nagel K., "Distributed intelligence in large scale..." (2002)
		[OBR+04] Okuyama F.Y. et al., "ELMS: An Environment Description Lang..." (2004)
		[PBT+02] Parenthoën M. et al., "Action Learning for Autonomous Virtual..." (2002)
		[PRT+01] Parenthoën M. et al., "Put Fuzzy Cognitive Maps to Work in..." (2001)
		[PTM+02] Parenthoën M. et al., "Autonomy and Proactive Perception for..." (2002)
		[PTM+02b] Parenthoën M. et al., "Believable Decision for Virtual Actors" (2002)
		[PTM+02c] Parenthoën M. et al., "Perception Active pour Acteurs Virtuels" (2002)
		[TR+95] Tambe M. et al., "Architectures for Agents that Track O..." (1995)

Simulation

		[BG+95] Blumberg B.M. et al., "Multi-Level Direction of Autonomous..." (1995)
		[Bar00] Barnes C., "Visual Programming Agents for Virtual..." (2000)
		[CH+97] Carlson D.A. et al., "Simulation Levels of Detail for Real-..." (1997)
		[GGB+03] Galland S. et al., "MaMA-s: An introduction to a..." (2003)
		[KMG+03] Koukam A. et al., "A Multiview Approach to Modeling and..." (2003)
		[Rey87] Reynolds C.W., "flocks, Herds, and Schools: A Distrib..." (1987)
		[TR+95] Tambe M. et al., "Architectures for Agents that Track O..." (1995)
		[VD+02] Vanbergue D. et al., "Approche multi-agent pour la simulation..." (2002)
		[WT+03] Wagner G. et al., "Agent-Oriented Modeling and Agent-Based..." (2003)

Virtual Reality

		[DOO+99] Duffy B.R. et al., "Reality and virtual reality in mobile..." (1999)
		[ST+99] Schmalstieg D. et al., "Real-time Bounding Box Area Computation" (1999)
		[TR+95] Tambe M. et al., "Architectures for Agents that Track O..." (1995)
		[WSH+05] Weyns D. et al., "Exploiting a Virtual Environment in a..." (2005)