Abstract
Teamwork is a critical capability in multi-agent environments. Many such environments mandate that the agents and agent-teams must be persistent i.e., exist over long periods of time. Agents in such persistent teams are bound together by their long-term common interests and goals. This paper focuses on flexible teamwork in such persistent teams. Unfortunately, while previous work has investigated flexible teamwork, persistent teams remain unexplored. For flexible teamwork, one promising approach that has emerged is model-based, i.e., providing agents with general models of teamwork that explicitly specify their commitments in teamwork. Such models enable agents to autonomously reason about coordination. Unfortunately, for persistent teams, such models may lead to coordination and communication actions that while locally optimal, are highly problematic for the team's long-term goals. We present a decision-theoretic technique based on Markov decision processes to enable persistent teams to overcome such limitations of the model-based approach. In particular, agents reason about expected team utilities of future team states that are projected to result from actions recommended by the teamwork model, as well as lower-cost (or higher-cost) variations on these actions. To accommodate real-time constraints, this reasoning is done in an any-time fashion. Implemented examples from an analytic search tree and some real-world domains are presented.
Similar content being viewed by others
References
A. G. Barto, S. J. Bradtke, and S. P. Singh, “Learning to act using real-time dynamic programming”, Artif.Intell., Vol. 72, pp. 81–138, 1995.
R. E. Bellman, Dynamic Programming, Princeton University Press, 1957.
M. Boddy and T. Dean, “Solving time-dependent planning problems”, in Proc.Int.Joint Conf.Artif. Intell., pp. 979–984.
C. Boutilier, T. Dean, and S. Hanks, “Decision theoretic planning: Structural assumptions and computational leverage”, J.Artif.Intell.Res., to appear.
K. Carley and D. Svoboda, “Modeling organizational adaptation as a simulated annealing process”, Sociol Methods Res., Vol. 25, pp. 136–168, 1996.
P. R. Cohen and H. J. Levesque, “Teamwork”, Nous, Vol. 35, 1991.
K. Decker and V. Lesser, “Designing a family of coordination algorithms”, in Proc.Int.Conf.Multi-Agent Syst., 1995.
E. Durfee and V. Lesser, “Partial global planning: A coordination framework for distributed planning”, IEEE Trans.Syst., Man Cybernet., Vol. 21, 1991.
J. Firby, “An investigation into reactive planning in complex domains”, in Proc.Nat.Conf.Artif. Intell. (AAAI), 1987.
S. Franklin and A. Graesser, “Is this an agent or just a program? A taxonomy for autonomous agents”, in Proc.3rd Int.Workshop on Agents, Theories, Architectures, and Languages, Springer-Verlag: New York, 1996.
B. Grosz and S. Kraus, “Collaborative plans for complex group actions”, Artif.Intell., Vol. 86, pp. 269–358, 1996.
B. J. Grosz and C. L. Sidner, “Plans for discourse”, in P. R. Cohen, J. Morgan, and M. Pollack, eds., Intentions in Communication, MIT Press: Cambridge, MA, pp. 417–445.
B. Hayes-Roth, L. Brownston, and R. V. Gen, “Multiagent collaboration in directed improvisation”, in Proc.Int.Conf.Multi-Agent Syst.(ICMAS-95), 1995.
T. Haynes, S. Sen, N. Arora, and R. Nadella, “An automated meeting scheduling system that utilizes user preferences”, in Proc.Int.Conf.Autonomous Agents (Agents'97), 1997.
E. Horvitz, “Models of continual computations”, in Proc.Nat.Conf.Artif.Intell.(AAAI), 1997.
L. Jacolin and R. Stengel, “Evaluation of a cooperative air-traffic management model using principled negotiation between intelligent agents”, in Proc.Nat.Conf.Am.Inst.Aeronaut.Astronaut.(AIAA), 1998.
N. Jennings, “Controlling cooperative problem solving in industrial multi-agent systems using joint intentions”, Artif.Intell., Vol. 75, 1995.
G. Kaminka and M. Tambe, “What is wrong with us? Improving robustness through social diagnosis”, in Proc.Nat.Conf.Artif.Intell.(AAAI), 1998.
D. Kinny, M. Ljungberg, A. Rao, E. Sonenberg, G. Tidhard, and E. Werner, “Planned team activity”, in C. Castelfranchi and E. Werner, eds., Artificial Social Systems, Lecture notes in AI 830.Springer: New York, 1992.
H. Kitano, M. Tambe, P. Stone, S. Coradesci, H. Matsubara, M. Veloso, I. Noda, E. Osawa, and M. Asada, “The RoboCup Synthetic Agents' Challenge”, in Proc.Int.Joint Conf.Artif.Intell.(IJCAI), 1997.
R. E. Korf, “Depth-first iterative-deepening: An optimal admissible tree search”, Artif.Intell., Vol. 27, pp. 97–109, 1985.
R. E. Korf, “Real-time heuristic search”, Artif.Intell., Vol. 42, pp. 189–211, 1990.
H. J. Levesque, P. R. Cohen, and J. Nunes, “On acting together”, in Proc.Nat.Conf.Artif.Intell., 1990.
T. M. Mitchell, R. M. Keller, and S. T. Kedar-Cabelli, “Explanation-based generalization: A unifying view”, Machine Learning, Vol. 1, pp. 47–80, 1986.
A. Newell, Unified Theories of Cognition, Harvard Univ. Press: Cambridge, MA, 1990.
M. L. Puterman, Markov Decision Processes, John Wiley & Sons: New York, 1994.
H. Raiffa, Decision Analysis, Addison Wesley: Reading, MA, 1968.
A. S. Rao, A. Lucas, D. Morley, M. Selvestrel, and G. Murray, “Agent-oriented architecture for air-combat simulation”, Technical Report Technical Note 42, The Australian Artificial Intelligence Institute, 1993.
C. Rich and C. Sidnen, “COLLAGEN: When agents collaborate with people”, in Proc.Int.Conf. Auton.Agents (Agents'97), 1997.
M. Tambe, “Agent architectures for flexible, practical teamwork”, in Proc.Nat.Conf.Artif.Intell. (AAAI), 1997a.
M. Tambe, “Towards flexible teamwork”, J.Artif.Intell.Res.(JAIR), Vol. 7, pp. 83–124, 1997b.
M. Tambe, J. Adibi, Y. Alonaizon, A. Erdem, G. Kaminka, S. Marsella, and I. Muslea, “Building agent teams using an explicit teamwork model and learning”, Artif.Intell., Vol. 110, pp. 215–240, 1999.
M. Tambe, J. Adibi, Y. Alonaizon, A. Erdem, G. Kaminka, S. Marsella, I. Muslea, and M. Tallis, “ISIS: Using an explicit model of teamwork in RoboCup97”, in RoboCup-97: The First Robot World Cup Soccer Games and Conferences, Springer-Verlag: Heidelberg, Germany, 1998.
M. Tambe, W. L. Johnson, R. Jones, F. Koss, J. E. Laird, P. S. Rosenbloom, and K. Schwamb, “Intelligent agents for interactive simulation environments”, AI Mag., Vol. 16, 1995.
M. Tambe and H. Jung, “The benefits of arguing in a team”, AI Mag., to appear.
M. Tambe, W. Shen, M. Mataric, D. Goldberg, P. Modi, D. Pynadath, Z. Qiu, and B. Salemi, “Teamwork in cyberspace: Using TEAMCORE to make agents team-ready”, in S. Murugesan, ed., AAAI FALL Symposium on Social Agents, 1999b.
M. Tambe and W. Zhang, “Towards flexible teamwork in persistent teams”, in Proc.Int.Conf.Multi-Agent Syst.(ICMAS), 1998.
W. Zhang and R. E. Korf, “Performance of linear-space search algorithms”, Artif.Intell., Vol. 79, pp. 241–292, 1995.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tambe, M., Zhang, W. Towards Flexible Teamwork in Persistent Teams: Extended Report. Autonomous Agents and Multi-Agent Systems 3, 159–183 (2000). https://doi.org/10.1023/A:1010026728246
Issue Date:
DOI: https://doi.org/10.1023/A:1010026728246