Share Email Print
cover

Proceedings Paper

Connectionist Learning Control at GTE Laboratories
Author(s): Judy A. Franklin; Richard S. Sutton; Charles W. Anderson; Oliver G. Selfridge; Daniel B. Schwartz
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

At GTE Laboratories, we are advancing the theory of connectionist learning architectures for real-time control while exploring their relationships to animal learning models, applications in manufacturing quality control, and VLSI implementations. We seek connectionist-network architectures with improved convergence rate and scaling properties, as assessed on simulated and actual control problems. Our primary focus is on extensions to reinforcement learning. These include adaptive critics, feature/representation adaptation in multilayer networks, hybrid connectionist/conventional controllers, and modular networks for hierarchical control. We are also extending methods for system identification, or model learning, to include internal models learned using temporal-differences. We propose the integration of reinforcement and model learning based on their relationships to dynamic programming. We are working to resolve how connectionist systems should serve as a total systems concept or as tools in a larger architecture.

Paper Details

Date Published: 1 February 1990
PDF: 12 pages
Proc. SPIE 1196, Intelligent Control and Adaptive Systems, (1 February 1990); doi: 10.1117/12.969923
Show Author Affiliations
Judy A. Franklin, GTE Laboratories Incorporated (United States)
Richard S. Sutton, GTE Laboratories Incorporated (United States)
Charles W. Anderson, GTE Laboratories Incorporated (United States)
Oliver G. Selfridge, GTE Laboratories Incorporated (United States)
Daniel B. Schwartz, GTE Laboratories Incorporated (United States)


Published in SPIE Proceedings Vol. 1196:
Intelligent Control and Adaptive Systems
Guillermo Rodriguez, Editor(s)

© SPIE. Terms of Use
Back to Top