Show simple item record

Policy gradient approaches for multi-objective sequential decision making: A comparison

contributor authorParisi, Simone
contributor authorPirotta, Matteo
contributor authorSmacchia, Nicola
contributor authorBascetta, Luca
contributor authorRestelli, Marcello
date accessioned2020-03-12T22:27:44Z
date available2020-03-12T22:27:44Z
date issued2014
identifier other7010618.pdf
identifier urihttps://libsearch.um.ac.ir:443/fum/handle/fum/1083823?show=full
formatgeneral
languageEnglish
publisherIEEE
titlePolicy gradient approaches for multi-objective sequential decision making: A comparison
typeConference Paper
contenttypeMetadata Only
identifier padid8221050
subject keywordsneural nets
subject keywordsn pattern classification
subject keywordsn AANN
subject keywordsn OCC
subject keywordsn STS-AANN
subject keywordsn auto-associative neural networks
subject keywordsn one-class neural network classifier
subject keywordsn optimal representative model
subject keywordsn selected training samples for associative neural network
subject keywordsn Biological neural networks
subject keywordsn Classification algorithms
subject keywordsn Joints
subject keywordsn Mathematical model
subject keywordsn Noise measurement
subject keywordsn Training
subject keywordsn Auto-Associative Neural Networks
subject keywordsn Noisy data
subject keywordsn One-Class
identifier doi10.1109/IJCNN.2014.6889429
journal titledaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2014 IEEE Symposium on
filesize19022736
citations1


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record