Abstract
This chapter presents a proposal to characterize sapient agents in terms of cognitive concepts and abilities. In particular, a sapient agent is considered a cognitive agent that learns its cognitive state and capabilities through experience. This characterization is based on formal concepts such as beliefs, goals, plans and reasoning rules, and formal techniques such as relational reinforcement learning. We identify several aspects of cognitive agents that can be evolved through learning and indicate how these aspects can be learned. Other important features such as the social environment, interaction with other agents or humans, and the ability to deal with emotions are also discussed. The chapter ends with directions for further research on sapient agents.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Boutilier, C., Reiter, R., and Price B. (2001). Symbolic dynamic programming for first-order MDP’s.In Bernhard Nebel, editor, Proc. of the 17th Int. Joint Conference on Artificial Intelligence (IJCAI-01), pages 690–697, San Francisco, CA, August 4–10 2001. Morgan Kaufmann.
Broersen, J., Dastani, M., Hulstijn, J., and van der Torre, L. (2002) and. Goal generation in the BOID architecture.Cognitive Science Quarterly, 2(3-4):428–447.
Crites, R. H., and Barto, A.G.,Improving elevator performance using reinforcement learning.In Touretzky, D.S., Mozer, M.C., and Hasselmo, M.E., editors, Advances in Neural Information Processing Systems 8, pages 1017–1023, Cambridge MA, 1996. MIT Press.
Damasio, A.R.,Descartes’ Error: Emotion, Reason and the Human Brain.Gosset/Putnam, New York, NY, 1994.
Dastani, M., de Boer, F., Dignum, F., and Meyer, J-J.Ch. Programming agent deliberation: An approach illustrated using the 3apl language.In Proc. of the Second Int. Conference on Autonomous Agents and Multiagent Systems (AAMAS’03). ACM Press, 2003a.
Dastani, M., Dignum, F., and Meyer, J-J.Ch. Autonomy and agent deliberation.In Proc. of The First Int. Workshop on Computatinal Autonomy - Potential, Risks, Solutions (Autonomous 2003), 2003b.
Dastani, M., van Riemsdijk, B., Dignum, F., and Meyer, J-J.Ch. A programming language for cognitive agents: Goal-directed 3APL.In Proc. the ProMAS 2003 Workshop at AAMAS’03, 2003c.
Dietterich, T.G. Hierarchical reinforcement learning with the MAXQ value function decomposition.Journal of Artificial Intelligence Research, 13:227–303, 2000.
d’Inverno, M., Kinny, D., Luck, M., and Wooldridge, M. A formal specification of dMARS.In Agent Theories, Architectures, and Languages, pages 155–176, 1997.
Dzeroski, S. Relational reinforcement learning for agents in worlds with objects.In Proc. of the Symposium on Adaptive Agents and Multi-Agent Systems (AISB’02), pages 1–8, 2002.
Koen V. Hindriks, Frank S. De Boer, Wiebe Van der Hoek, and John-Jules Ch. Meyer. Agent programming in 3apl.Autonomous Agents and Multi-Agent Systems, 2(4):357–401, 1999.
Kaelbling, L. P., Oates, T., Hernandez, N., and Finney, S.Learning in worlds with objects.In The AAAI Spring Symposium, March 2001.
Littman, M. L., and Boyan, J. A. A distributed reinforcement learning scheme for network routing. In J. Alspector, R. Goodman, and T.X. Brown, editors, Proc. of the First Int. Workshop on Applications of Neural Networks to Telecommunication, pages 45–51, Hillsdale, New Jersey, 1993.
Ortony, A., Clore, G. L., and Collins, A.The cognitive structure of emotions.Cambridge University Press, Cambridge, MA, 1988.
Parr, R. and Russell, S.Reinforcement learning with hierarchies of machines.In Advances in Neural Information Processing Systems 11,1997.
Picard, R. W.Affective Computing.MIT Press, Cambridge, MA, 1997.
Rao, A. S. AgentSpeak(L): BDI agents speak out in a logical computable language. In Rudy van Hoe, editor, Seventh European Workshop on Modelling Autonomous Agents in a Multi-Agent World, Eindhoven, The Netherlands, 1996.
Rao, A.S. and Georgeff, M. P.Modeling rational agents within a BDI architecture.In Proc. of Second Int. Conference on Knowledge Representation and Reasoning (KR’91), pages 473–484. Morgan Kaufmann, 1991.
Rao, A. S. and Georgeff, M. P.BDI agents: from theory to practice.In Proc. of the Int. Conference on Multi-Agent Systems (ICMAS’95), pages 312–319, 1995.
Reiter, R.Knowledge in Action: Logical Foundations for Specifying and Implementing Dynamical Systems. The MIT Press, Cambridge, Massachusetts, 2001.
Sutton, R.S. and Barto, A.G. Reinforcement Learning: an Introduction.The MIT Press, Cambridge, 1998.
Sutton, R.S. Precup, D. and Singh, S. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning.Artificial Intelligence, 112(1–2):181–211, 1999.
Tan, M.Multi-agent reinforcement learning: Independent vs. cooperative agents.In Proc. of the Tenth Int. Conference on Machine Learning, pages 330–337, June 1993.
Tesauro, G. Practical issues in temporal difference learning. In D. S. Lippman, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 4, pages 259–266. San Mateo, CA: Morgan Kaufmann, 1992.
van Otterlo, M.Relational expressions in reinforcement learning: Review and open problems.In E. de Jong and T. Oates, editors, Proc. of the ICML’02 Workshop on Development of Representations,2002.
van Otterlo, M.Efficient reinforcement learning using relational aggregation.In Proc. of the Sixth European Workshop on Reinforcement Learning, Nancy, France (EWRL-6), 2003.
van Otterlo, M.A survey of reinforcement learning in relational domains.Technical Report TR-CTIT-05-31, July 2005, 70 pp, CTIT Technical Report Series, ISSN 1381-3625, Department of Computer Science, University of Twente, 2005.
Watkins, C. J. C. H.Learning from Delayed Rewards.PhD thesis, King’s College, Cambridge, England, 1989.
Weiss, G.Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence.The MIT Press, Cambridge, Massachusets, 1999.
Wiering, M. A.Multi-agent reinforcement learning for traffic light control.In P. Langley, editor, Proc. of the Seventeenth Int. Conference on Machine Learning, pages 1151–1158, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag London Limited
About this chapter
Cite this chapter
Otterlo, M.v., Dastani, M., Wiering, M., Meyer, JJ. (2008). A Characterization of Sapient Agents. In: Mayorga, R.V., Perlovsky, L.I. (eds) Toward Artificial Sapience. Springer, London. https://doi.org/10.1007/978-1-84628-999-6_9
Download citation
DOI: https://doi.org/10.1007/978-1-84628-999-6_9
Publisher Name: Springer, London
Print ISBN: 978-1-84628-998-9
Online ISBN: 978-1-84628-999-6
eBook Packages: Computer ScienceComputer Science (R0)