USAK method for the reinforcement learning

Скорочена інформація про документ
dc.contributor.authorNovotarskyi, Mykhailo
dc.contributor.authorKuzmich, Valentin
dc.date.accessioned2023-04-18T08:30:30Z
dc.date.available2023-04-18T08:30:30Z
dc.date.issued2020
dc.description.abstractIn the field of reinforcement learning, tabular methods have become widespread. There are many important scientific results, which significantly improve their performance in specific applications. However, the application of tabular methods is limited due to the large amount of resources required to store value functions in tabular form under high-dimensional state spaces. A natural solution to the memory problem is to use parameterized function approximations. However, conventional approaches to function approximations, in most cases, have ceased to give the desired result of memory reduction in solving real world problems. This fact became the basis for the application of new approaches, one of which is the use of Sparse Distributed Memory (SDM) based on Kanerva coding. A further development of this direction was the method of Similarity-Aware Kanerva (SAK). In this paper, a modification of the SAK method is proposed, the Uniform Similarity-Aware Kanerva (USAK) method, which is based on the uniform distribution of prototypes in the state space. This approach has reduced the use of RAM required to store prototypes. In addition, reducing the receptive distance of each of the prototypes made it possible to increase the learning speed by reducing the number of calculations in the linear approximator.uk
dc.format.pagerangePp. 4-14uk
dc.identifier.citationNovotarskyi, M. USAK method for the reinforcement learning / Novotarskyi Mykhailo, Valentin Kuzmich // Information, Computing and Intelligent systems. – 2020. – No. 1. – Pp. 4–14. – Bibliogr.: 19 ref.uk
dc.identifier.doihttps://doi.org/10.20535/2708-4930.1.2020.216042
dc.identifier.orcid0000-0002-5653-8518uk
dc.identifier.orcid0000-0002-6077-3609uk
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/54656
dc.language.isoenuk
dc.publisherNational Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"uk
dc.publisher.placeKyivuk
dc.relation.ispartofInformation, Computing and Intelligent systems, No. 1uk
dc.subjectreinforcement learninguk
dc.subjectKanerva codinguk
dc.subjectfunction approximationuk
dc.subjectprototypeuk
dc.subjectvalue functionuk
dc.subject.udc004.056.57:032.26uk
dc.titleUSAK method for the reinforcement learninguk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
216042-488193-1-10-20201111.pdf
Розмір:
799.66 KB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.1 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Information, Computing and Intelligent systems, No. 1