Training Reinforcement Neurocontrollers Using the Polytope Algorithm

Simple item page
dc.creatorLikas, A.
dc.creatorLagaris, I. E.
dc.date1998-12-03
dc.date.accessioned2026-07-07T03:23:51Z
dc.date.available2026-07-07T03:23:51Z
dc.descriptionA new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorithm to adjust the weights of the action network so that a simple direct measure of the training performance is maximized. Experimental results from the application of the method to the pole balancing problem indicate improved training performance compared with critic-based and genetic reinforcement approaches.
dc.identifierhttps://arxiv.org/abs/cs/9812002
dc.identifierhttp://arxiv.org/abs/cs/9812002
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33103
dc.subjectNeural and Evolutionary Computing
dc.subjectC.1.3
dc.titleTraining Reinforcement Neurocontrollers Using the Polytope Algorithm
dc.typetext

Files

Collections

arXiv