Abstract
The Tartarus problem is a box pushing task in a grid world environment. It is one of difficult problems for purely reactive agents to solve, and thus a memory-based control architecture is required. This paper presents a novel control structure, called tree state machine, which has an evolving tree structure for sensorimotor mapping and also encodes internal states. As a result, the evolutionary computation on tree state machines can quantify internal states and sensor states needed for the problem. Tree state machines with a dynamic feature of sensor states are demonstrated and compared with finite state machines and GP-automata. It is shown that both sensor states and memory states are important factors to influence the behavior performance of an agent.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ashlock, D.: GP-automata for dividing the dollar. In: Genetic Programming 1997, pp. 18–26. MIT Press, Cambridge (1997)
Ashlock, D.: ISAc lists, a different representation for program induction. In: Genetic Programming 1998, pp. 3–10. Morgan Kauffman, San Francisco (1998)
Bakker, B., de Jong, M.: The epsilon state count. From Animals to Animats 6, 51–60 (2000)
Balakrishnan, K., Honavar, V.: On sensor evolution in robotics. In: Proceedings of the first Conf. on Genetic Programming, pp. 455–460. MIT Press, Cambridge (1996)
Gathercole, C.: An Investigation of Supervised Learning in Genetic Programming. Ph. D. dissertation, University of Edinburgh (1998)
Hopcroft, J.E., Ullman, J.D.: Introduction to automata theory, languages, and computation. Addison Wesley, Reading (1979)
Jefferson, D., Collins, R.: Evolution as a theme in artificial life. In: Langton, C. (ed.) Artificial Life II, Addison-Wesley, Reading (1991)
Kim, D., Hallam, J.: Mobile robot control based on Boolean logic with internal memory. In: Kelemen, J., SosÃk, P. (eds.) ECAL 2001. LNCS (LNAI), vol. 2159, pp. 529–538. Springer, Heidelberg (2001)
Kim, D., Hallam, J.: An evolutionary approach to quantify internal states needed for the Woods problem. From Animals to Animats 7, 312–322 (2002)
Koza, J.R.: Genetic Programming. MIT Press, Cambridge (1992)
Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge (2000)
Silva, A., Neves, A., Costa, E.: Genetically programming networks to evolve memory mechanism. In: Genetic and Evolutionary Computation Conference (1999)
Teller, A.: The evolution of mental models. In: Advances in Genetic Programming, MIT Press, Cambridge (1994)
Wilson, S.W.: ZCS: A zeroth level classifier system. Evolutionary Computation 2(1), 1–18 (1994)
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
Kim, D. (2004). Analyzing Sensor States and Internal States in the Tartarus Problem with Tree State Machines. In: Yao, X., et al. Parallel Problem Solving from Nature - PPSN VIII. PPSN 2004. Lecture Notes in Computer Science, vol 3242. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30217-9_56
Download citation
DOI: https://doi.org/10.1007/978-3-540-30217-9_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23092-2
Online ISBN: 978-3-540-30217-9
eBook Packages: Springer Book Archive