The Community for Technology Leaders
Computational Intelligence in Robotics and Automation, IEEE International Symposium on (1997)
Monterey, CA
June 10, 1997 to June 11, 1997
ISBN: 0-8186-8138-1
pp: 234
Ron Sun , University of Alabama, Tuscaloosa
Todd Peterson , University of Alabama, Tuscaloosa
ABSTRACT
To deal with reactive sequential decision tasks, we present a learning model { CLARION}, which is a hybrid connectionist model consisting of both localist and distributed representations, based on the two-level approach proposed in Sun (1995). The model learns and utilizes procedural and declarative knowledge, tapping into the synergy of the two types of processes. It unifies neural, reinforcement, and symbolic methods to perform on-line, bottom-up learning. Experiments in various situations are reported that shed light on the working of the model.
INDEX TERMS
neural networks, reinforcement learning, hybrid models procedurtal knowledge, declarative knowledge
CITATION

T. Peterson and R. Sun, "A Hybrid Model for Learning Sequential Navigation," Computational Intelligence in Robotics and Automation, IEEE International Symposium on(CIRA), Monterey, CA, 1997, pp. 234.
doi:10.1109/CIRA.1997.613863
93 ms
(Ver 3.3 (11022016))