Learning with Binary-Valued Utility Using Derivative Adaptive Critic Methods
Published In
IEEE International Conference on Neural Networks - Conference Proceedings
Document Type
Citation
Publication Date
12-1-2004
Abstract
Adaptive critic methods for reinforcement learning are known to provide consistent solutions to optimal control problems, and are also considered plausible models for cognitive learning processes. This work discusses binary reinforcement in the context of three adaptive critic methods: heuristic dynamic programming (HDP), dual heuristic programming (DHP), and globalized dual heuristic programming (GDHP). Binary reinforcement arises when the qualitative measure of success is simply "pass" or "fail". We implement binary reinforcement with adaptive critic methods for the pole-cart benchmark problem. Results demonstrate two qualitatively dissimilar classes of controllers: those that replicate the system stabilization achieved with quadratic utility, and those that merely succeed at not dropping the pole. It is found that the GDHP method is effective for learning an approximately optimal solution, with results comparable to those obtained via DHP that uses a more informative, quadratic utility function.
Locate the Document
https://doi.org/10.1109/IJCNN.2004.1380882
DOI
10.1109/IJCNN.2004.1380882
Persistent Identifier
https://archives.pdx.edu/ds/psu/37312
Citation Details
Matzner, S. A., Shannon, T. T., & Lendaris, G. G. (2004, July). Learning with binary-valued utility using derivative adaptive critic methods. In 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No. 04CH37541) (Vol. 3, pp. 1805-1810). IEEE.