An integrated framework for adaptive reasoning about conversation patterns

ABSTRACT

We present an integrated approach for reasoning about and learning conversation patterns in multiagent communication. The approach is based on the assumption that information about the communication language and protocols available in a multiagent system is provided in the form of dialogue sequence patterns, possibly tagged with logical conditions and instance information. We describe an integrated social reasoning architecture m²InFFrA that is capable of (i) processing such patterns, (ii) making communication decisions in a boundedly rational way, and (iii) learning patterns and their strategic application from observation.

REFERENCES

• 1: Frank Dignum, Advances in Agent Communication: International Workshop on Agent Communication Languages, Acl 2003, Melbourne, Australia, July 14, 2003: Revised and Invited Papers (Lecture Notes in Computer Science, 2922.), SpringerVerlag, 2004
• 2: F. Fischer and M. Rovatsos. Reasoning about Communication: A Practical Approach based on Empirical Semantics. In Proceedings of the 8th International Workshop on Cooperative Information Agents (CIA), Erfurt, Germany, 2004. Springer.
• 3: Felix Fischer , Michael Rovatsos , Gerhard Weiss, Acquiring and adapting probabilistic models of agent conversation, Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems, July 25-29, 2005, The Netherlands [doi>10.1145/1082473.1082490]
• 4: LIESON. http://www7.in.tum.de/~rovatsos/lieson, 2002--2004.
• 5: Doina Precup , Richard S. Sutton, Temporal abstraction in reinforcement learning, 2000
• 6: M. Rovatsos. Computational Interaction Frames. PhD thesis, Department of Informatics, Technical University of Munich, 2004.
• 7: M. Rovatsos, F. Fischer, and G. Weiss. Hierarchical Reinforcement Learning for Communicating Agents. In Proceedings of the Second European Workshop on Multiagent Systems (EUMAS), Barcelona, Spain, 2004.
• 8: Michael Rovatsos , Matthias Nickles , Gerhard Weiss, Interaction is meaning: a new model for communication in open systems, Proceedings of the second international joint conference on Autonomous agents and multiagent systems, July 14-18, 2003, Melbourne, Australia [doi>10.1145/860575.860661]

INDEX TERMS

General Terms:
Languages, Theory

Keywords:
agent communication, evolutionary semantics, interaction frames, social reasoning