Abstract
This paper presents a new method for predicting the values of policies for cloned multiple teleo-reactive robots operating in the context of exogenous events. A teleo-reactive robot behaves autonomously under the control of a policy and is pre-disposed by that policy to achieve some goal. Our approach plans for a set of conjoint robots by focusing upon one representative of them. Simulation results reported here indicate that our method affords a good degree of predictive power and scalability.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Benson, S.: Learning Action Models for Reactive Autonomous Agents, PhD, Dept. of Computer Science, Stanford University (1996)
Broda, K., Hogger, C.J., Watson, S.: Constructing Teleo-Reactive Robot Programs. In: Proceedings of the 14th European Conference on Artificial Intelligence, Berlin, pp. 653–657 (2000)
Broda, K., Hogger, C.J.: Designing Teleo-Reactive Programs, Technical Report 2003/8, Dept. of Computing, Imperial College London, UK (2003)
Broda, K., Hogger, C.J.: Designing and Simulating Individual Teleo-Reactive Agents. In: Poster Proceedings, 27th German Conference on Artificial Intelligence, Ulm (2004)
Cassandra, A.R., Kaelbling, L.P., Littman, M.: Acting Optimally in Partially Observable Stochastic Domains. In: Proceedings 12th National Conference on AI (AAAI 1994), Seattle, pp. 183–188 (1994)
Chades, I., Scherrer, B., Charpillet, F.: Planning Cooperative Homogeneous Multiagent Systems using Markov Decision Processes. In: Proceedings of the 5th International Conference on Enterprise Information Systems (ICEIS 2003), pp. 426–429 (2003)
Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and Acting in Partially Observable Stochastic Domains. Artificial Intelligence 101, 99–134 (1998)
Kochenderfer, M.: Evolving Hierarchical and Recursive Teleo-reactive Programs through Genetic Programming. In: Ryan, C., Soule, T., Keijzer, M., Tsang, E.P.K., Poli, R., Costa, E. (eds.) EuroGP 2003. LNCS, vol. 2610, pp. 83–92. Springer, Heidelberg (2003)
Mitchell, T.: Reinforcement Learning, Machine Learning,, pp. 367–390. McGraw Hill, New York (1997)
Nair, R., Tambe, M., Yokoo, M., Pynadath, D., Marsella, M.: Taming Decentralised POMDPs: Towards Efficient Policy Computation for Multiagent Settings. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI 2003), pp. 705–711 (2003)
Nilsson, N.J.: Teleo-Reactive Programs for Agent Control. Artificial Intelligence Research 1, 139–158 (1994)
Nilsson, N.J.: Teleo-Reactive Programs and the Triple-Tower Architecture. Electronic Transactions on Artificial Intelligence 5, 99–110 (2001)
Rathnasabapathy, B., Gmytrasiewicz, P.: Formalizing Multi-Agent POMDPs in the Context of Network Routing. In: Proceedings of 36th Hawaii International Conference on System Sciences, HICSS 2003 (2003)
Ryan, M.R.K., Pendrith, M.D.: An Architecture for Modularity and Re-Use in Reinforcement Learning. In: Proceedings of the 15th International Conference on Machine Learning, Madison, Wisconsin (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Broda, K., Hogger, C.J. (2004). Policies for Cloned Teleo-reactive Robots. In: Lindemann, G., Denzinger, J., Timm, I.J., Unland, R. (eds) Multiagent System Technologies. MATES 2004. Lecture Notes in Computer Science(), vol 3187. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30082-3_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-30082-3_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23222-3
Online ISBN: 978-3-540-30082-3
eBook Packages: Springer Book Archive