Abstract
This paper proposes an adaptive planning system design based on the weightless net paradigm[1]. The system learns local state transitions through ’exploration’ of the application environment and then generalizes on the learnt data — enabling the system to produce optimal plans based on action cost. The generalization also allows data to be trained into the planner during the generalization process, allowing the planner to adapt relevant plans according to the new data. A simulation of the proposed system has been implemented and successfully applied to several problem domains. The amount of computation during operation of this system is less than that of a conventional rule-based planner.
Preview
Unable to display preview. Download preview PDF.
References
I.Aleksander, Ideal Neurons for Neural Computers, Parallel Processing on Neural Systems and Computers, Ed. R. Eckmiller/G.Hartmann/G.Hauske,pp.225–228, North-Holland, 1990
I.Aleksander, The logic of Connectionist Systems, Neural Computing Architectures, MIT Press, 1988
Thomas J. Tighe, Modern Learning Theory, Oxford University Press, 1982
J.Mrsic-Flogel, NEMESYS — modelling system for weightless nets,ICANN91,Elsevier, 1991
M.Drummond,1989, AI Planning-A Tutorial and Review, NASA Report,AIAI-TR-30
J.Mrsic-Flogel.Cognitive Planning with Weightless Systems,Proc. of ICANN92 conference, Ed. I.AIeksander and J. Taylor,Elsevier,1992
J.Mrsic-Flogel,Aspects of Planning with Neural Systems, PhD Thesis, Imperial College, November 1992
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mrsic-Flögel, J. (1993). Planlite: Adaptive planning using weightless systems. In: Mira, J., Cabestany, J., Prieto, A. (eds) New Trends in Neural Computation. IWANN 1993. Lecture Notes in Computer Science, vol 686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-56798-4_225
Download citation
DOI: https://doi.org/10.1007/3-540-56798-4_225
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-56798-1
Online ISBN: 978-3-540-47741-9
eBook Packages: Springer Book Archive