Open Access
Open access
Lecture Notes in Computer Science, том 12960 LNAI, номера страниц: 13-24

Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory

Тип документа: Book Chapter
Дата публикации: 2021-09-14
Springer Nature
Springer Nature
Название журнала:  Lecture Notes in Computer Science
Квартиль по SCImago: 3
Квартиль по Web of Science: —
Импакт-фактор 2021: —
ISSN: 03029743, 16113349
Краткое описание
In this paper, we propose a biologically plausible model for learning the decision-making sequence in an external environment with internal motivation. As a computational model, we propose a hierarchical architecture of an intelligent agent acquiring experience based on reinforcement learning. We use the basal ganglia model to aggregate a reward, and sparse distributed representation of states and actions in hierarchical temporal memory elements. The proposed architecture allows the agent to build a compact model of the environment and to form an effective strategy, which is experimentally demonstrated to search for resources in grid environments.
Цитируется в публикациях: 2
По дате По цитируемости
Метрики

Поделиться

Цитировать
ГОСТ |
Цитировать
ГОСТ Копировать
1. Dzhivelikian E. и др. Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory // Lecture Notes in Computer Science. 2021. С. 13–24.
RIS |
Цитировать
RIS Копировать

TY - GENERIC

DO - 10.1007/978-3-030-86993-9_2

UR - http://dx.doi.org/10.1007/978-3-030-86993-9_2

TI - Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory

T2 - Brain Informatics

AU - Dzhivelikian, Evgenii

AU - Latyshev, Artem

AU - Kuderov, Petr

AU - Panov, Aleksandr I.

PY - 2021

PB - Springer International Publishing

SP - 13-24

SN - 0302-9743

SN - 1611-3349

ER -

BibTex |
Цитировать
BibTex Копировать

@incollection{Dzhivelikian_2021,

doi = {10.1007/978-3-030-86993-9_2},

url = {https://doi.org/10.1007%2F978-3-030-86993-9_2},

year = 2021,

publisher = {Springer International Publishing},

pages = {13--24},

author = {Evgenii Dzhivelikian and Artem Latyshev and Petr Kuderov and Aleksandr I. Panov},

title = {Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory},

booktitle = {Brain Informatics}

}

MLA
Цитировать
MLA Копировать
Dzhivelikian, Evgenii et al. “Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory.” Lecture Notes in Computer Science (2021): 13–24. Crossref. Web.