As we have mentioned earlier, Mitchell (1990) ascribes three learning goals to an agent: becoming more perceptive, more correct, and more reactive. These are the goals that an external observer might ascribe to an agent when observing its behaviour over time.
If an observer were to observe a multi-agent system, which learning goals could he ascribe to individual agents? We believe that the list of learning goals mentioned by Mitchell could be extended to include at least one additional requirement. We could require that the agent should become increasingly more integrated, that is, play its proper role in the community of agents. This involves being called upon by other agents, recognizing when to delegate a problem to others and exploiting these opportunities.
Acknowledgments
The work of P. Brazdil and L. Torgo discussed in this paper was supported by Esprit 2 Project Ecoles (3059). The authors wish to thank the Commission of European Communities for their support.
References
Baker M. (1991): "A Model for Negotiation in Intelligent Tutoring Dialogs", in New Directions for ITS, E.Costa (ed.), to be published by Springer Verlag.
Bond A. and Gasser. L. (eds.) (1988): Readings in DAI, Morgan Kaufmann Publishers, San Mateo.
Brazdil P. and Torgo L. (1990): "Knowledge Acquisition via Knowledge Integration", in Current Trends in Artificial Intelligence, B. Wielinga et al. (eds.), IOS Press, Amsterdam, 1990.
Brazdil P. and Muggleton S. (1991): "Learning to Relate Terms in Multiple Agent Environment", in this volume.
Buntine W. (1889): "Learning Classification Rules Using Bayes", in Proceedings of 6th International Workshop on Machine Learning, Ithaca, New York.
Demazeau Y. and J.-P. Mueller (eds.) (1991): Proceedings of the 2nd European Workshop on Modelling Autonomous Agents and Multi-Agent Worlds (MAAMAW 90), Saint-Quentin-en-Yvelines, France, August 1990, Elsevier Science Publishers.
Durfee E., Lesser V.R. and Corkill D.D. (1989): "Cooperative Distributed Problem Solving", in The Handbook of Artificial Intelligence, Volume IV, Barr A., Cohen P.R. and Feigenbaum E.A. (eds.), Addison Wesley, 1989.
Gams M. (1989): "The Measurement Highlight the Importance of Redundant Knowledge", in Proceedings of 4th European Working Session on Machine Learning (EWSL-89), K. Morik (ed.), pp. 71-80, Pitman - Morgan Kaufmann.
Gams M., Bohanec M. and Cestnik B. (1990): A Schema for Using Multiple Knowledge, Working Paper, Jozef Stefan Institute, Ljubljana, Yugoslavia.
Huhns M. (ed.) (1987): Distributed AI Vol.1, Pitman and Morgan Kaufmann, 1987.
Janikow C.Z. (1989): "The AQ16 Inductive Learning Program: Some Experimental Results with AQ16 and Other Symbolic and Nonsymbolic Programs", Rep. of AI Center, George Mason University.
Mitchell T. (1990): "Becoming Increasingly Reactive", in Proceedings of 8th National Conference on Artificial Intelligence (AAAI-90), Morgan Kaufmann, pp. 1051-1058.
Oliveira E., Camacho R. and Ramos C. (1990): A Multi-Agent Environment in Robotics, Working Paper, Fac. of Engineering, Univ. of Porto, (also LIACC, Univ. of Porto), Portugal.
Schlimmer J.C. and Fisher D. (1986): "A Case Study of Incremental Concept Induction", in Proceedings of the Fifth National Conference on Artificial Intelligence, pp. 496-501, Morgan Kaufmann.
Sian S. (1991a): "Adaptation Based on Cooperative Learning in Multi-Agent Systems", in Proceedings of the 2nd European Workshop on Modelling Autonomous Agents and Multi-Agent Worlds (MAAMAW 90), Demazeau Y. and J.-P. Mueller (eds.), Saint-Quentin-en-Yvelines, France, August 1990, Elsevier Science Publishers.
Sian S. (1991b): Extending Learning to Multiple Agents: Issues and a Model for Multi-Agent Machine Learning (MA-ML), in this volume.
Shaw M. and Gaines B. (1989): Knowledge Acquisition: Some Foundations, manual Methods and Future Trends, in Proceedings of Third European Workshop on Knowledge Acquisition for Knowledge-Based Systems, J. Boose, B. Gaines and J.G. Ganascia (eds.), Paris, July 1989.
Utgoff P.E. (1988): "ID5: An Incremental ID3", in Proc. of 5th International Workshop on Machine Learning, J. Laird (ed.), Ann Harbour, Morgan Kaufmann Inc.
van de Velde W.(ed.) (1990): Towards Learning Robots, North Holland, Amsterdam.