Abstract
A linearly anticipatory agent architecture for learning in multi-agent systems is presented. It integrates low-level reaction with high-level deliberation by embedding an ordinary reactive system based on situation-action rules, called the Reactor, in an anticipatory agent forming a layered hybrid architecture. By treating all agents in the domain (itself included) as being reactive, this approach reduces the amount of search needed while at the same time requiring only a small amount of heuristic domain knowledge. Instead it relies on a linear anticipation mechanism, carried out by the Anticipator, to learn new reactive behaviors. The Anticipator uses a world model (in which all agents are represented only by their Reactor) to make a sequence of one-step predictions. After each step it checks whether an undesired state has been reached. If this is the case it will adapt the actual Reactor in order to avoid this state in the future. Results from simulations on learning reactive rules for cooperation and coordination of teams of agents indicate that the behavior of this type of agents is superior to that of the corresponding reactive agents. Also some promising results from simulations of competing self-interested agents are presented.
Preview
Unable to display preview. Download preview PDF.
References
D. Carmel and S. Markovitch. Opponent modeling in multi-agent systems. In G. Weiss and S. Sen, editors, Adaptation and Learning in Multi-Agent Systems (LNAI 1042), pages 40–52. Springer Verlag, 1996.
P. Davidsson. Autonomous Agents and the Concept of Concepts. PhD thesis, Department of Computer Science, Lund University, Sweden, 1996.
P. Davidsson, E. Astor, and B. Ekdahl. A framework for autonomous agents based on the concept of anticipatory systems. In Cybernetics and Systems '94, pages 1427–1434. World Scientific, 1994.
T. Dean and M. Boddy. An analysis of time-dependent planning. In AAAI-88, pages 49–54. Morgan Kaufmann, 1988.
M. Drummond and J. Bresina. Anytime synthetic projection: Maximizing the probability of goal satisfaction. In AAAI-90, pages 138–144. MIT Press, 1990.
B. Ekdahl, E. Astor, and P. Davidsson. Towards anticipatory agents. In M. Wooldridge and N.R. Jennings, editors, Intelligent Agents — Theories, Architectures, and Languages (LNAI 890), pages 191–202. Springer Verlag, 1995.
E. Gat. Integrating planning and reacting in a heterogeneous asynchronous architecture for controlling real-world mobile robots. In AAAI-92, pages 809–815. MIT Press, 1992.
P.J. Gmytrasiewicz and E.H. Durfee. Rational interaction in multiagent environment: Coordination. (submitted for publication), 1996.
S. Hanks, M. Pollack, and P. Cohen. Benchmarks, testbeds, controlled experimentation, and the design of agent architectures. AI Magazine, 14(4): 17–42, 1993.
D.N. Kinny and M.P. Georgeff. Commitment and effectiveness of situated agents. In IJCAI-91, pages 82–88. Morgan Kaufmann, 1991.
M. Minsky. The Society of Mind. Simon and Schuster, 1986.
Y. Mor, C.V. Goldman, and J.S. Rosenschein. Learn your opponent's strategy (in polynomial time!). In G. Weiss and S. Sen, editors, Adaptation and Learning in Multi-Agent Systems (LNAI 1042), pages 164–176, 1996.
R. Rosen. Anticipatory Systems — Philosophical, Mathematical and Methodological Foundations. Pergamon Press, 1985.
R.S. Sutton. First results with Dyna, an integrated architecture for learning, planning and reacting. In W.T. Miller, R.S. Sutton, and P.J. Werbos, editors, Neural Networks for Control, pages 179–189. MIT Press, 1990.
S. Zilberstein and S.J. Russell. Anytime sensing, planning and action: A practical model for robot control. In IJCAI-93, pages 1402–1407. Morgan Kaufmann, 1993.
G. Zlotkin and J.S. Rosenschein. Coalition, cryptography, and stability: Mechanisms for coalition formation in task oriented domain. In AAAI-94, pages 432–437. MIT Press, 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Davidsson, P. (1997). Learning by linear anticipation in multi-agent systems. In: Weiß, G. (eds) Distributed Artificial Intelligence Meets Machine Learning Learning in Multi-Agent Environments. LDAIS LIOME 1996 1996. Lecture Notes in Computer Science, vol 1221. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62934-3_41
Download citation
DOI: https://doi.org/10.1007/3-540-62934-3_41
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62934-4
Online ISBN: 978-3-540-69050-4
eBook Packages: Springer Book Archive