Abstract
Dynamical control with adaptive range coding eliminates fundamental shortcomings found in earlier applications of range (course) coding which used fixed partitioning. Adaptive range coding has the advantages of efficient implementation, execution and generalization. With the adaptive algorithm, region shapes are continually adjusted during operation and will self-organize to reflect the global dynamics of the system and the environment. The system progressively develops a control map relating environmental states, control actions, and future reinforcements.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Albus JS (1981) Brains, behavior, and robotics. Byte Books, McGraw-Hill, Peterburough, NH
Alkon DL (1989) Memory storage and neural systems. Scientific American, 261:1 (July)
Barto AG, Sutton RS, Anderson CW (1982) Neuron-like elements that can solve difficult learning control problems. Coins Tech Rep No. 82-20
Barto AG, Sutton RS, Anderson CW (1983) Neuron-like elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13:834–846
Cannon RH Jr (1967) Dynamics of physical systems. McGraw-Hill, New York
Cheok KC, Loh HK (1987) A ball-balancing demonstration of optimal and disturbance accommodating control. IEEE Control Syst Mag, pp. 54–57
Feldman JA, Ballard DH (1982) Connectionist models and their properties. Cogn Sci 6:205–254
Kan W, Aleksander I (1987) A probabilistic logic network for associative learning. In: Proceedings of the First Annual International Conference on Neural Networks
Klopf H (1982) The hedonistic neuron: a theory of memory, learning, and intelligence. Harper & Row/Hemisphere, New York
Kohonen T (1984) Self-organizaiton and associative memory. Springer, New York Berlin Heidelberg
McGaugh JL, Weinberger NM, Lynch G, Granger RH (1985) Neural mechanisms of learning and memory: cells, systems and computations. Naval Research Reviews 4
Michie D, Chambers R (1968) Machine Intelligence. In: Dale E, Michie D (eds). Oliver & Boyd, Edinburgh, p 137
Minsky M (1961) Steps toward artificial intelligence. Proc IRE 49,8
Ritter H, Schulten K (1986) Topology conserving mappings for learning motor tasks. In: Denker JS (ed) Neural networks for computing. AIP Conf. Proc. 151. Snowbird, Utah
Ritter H, Schulten K (1988) Extending Kohonen's self-organizing mapping algorithm to learn ballistic movements. In: Eckmiller R (ed) Neural computers. Springer, Berlin Heidelberg New York
Schneider GE (1973) Early lesions of the superior colliculus: factors affecting the formation of abnormal retinal projections. Brain Behav Evol 8: 73–109
Sutton RS (1984) Temporal credit assignment in reinforcement learning. Doctoral dissertation, University of Massachusetts
Sutton RS (1987) Learning to predict by the methods of temporal differences. Technical Report TR87–5091, GTE Laboratories Incorporated, Waltham, MA
Sutton RS, Barto AG (1987) A temporal-difference model of classical conditioning. GTE Tech Report TR87-509. 2, GTE Laboratories Incorporated
Weinberger NM, Hopkins W, Diamond DM (1984) Physiological plasticity of single neurons in auditory cortex of cat during acquisition of the pupillary conditioned response: I. Primary field (AI). Behav Neurosci 98:171–188
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Rosen, B.E., Goodwin, J.M. & Vidal, J.J. Process control with adaptive range coding. Biol. Cybern. 66, 419–428 (1992). https://doi.org/10.1007/BF00197722
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00197722