Open Access
Lecture Notes in Computer Science, volume 12960 LNAI, pages 13-24
Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory
Publication type: Book Chapter
Publication date: 2021-09-14
Journal:
Lecture Notes in Computer Science
Quartile SCImago
Q3
Quartile WOS
—
Impact factor: —
ISSN: 03029743, 16113349, 18612075, 18612083
Abstract
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.
Citations by journals
1
|
|
Brain Informatics
|
Brain Informatics
1 publication, 50%
|
Procedia Computer Science
|
Procedia Computer Science
1 publication, 50%
|
1
|
Citations by publishers
1
|
|
Springer Nature
|
Springer Nature
1 publication, 50%
|
Elsevier
|
Elsevier
1 publication, 50%
|
1
|
- We do not take into account publications that without a DOI.
- Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
- Statistics recalculated weekly.
{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2022],"ids":[0],"codes":[0],"imageUrls":[""],"datasets":[{"label":"Citations number","data":[2],"backgroundColor":["#3B82F6"],"percentage":["100"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Brain Informatics","Procedia Computer Science"],"ids":[17862,14281],"codes":[0,0],"imageUrls":["\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp"],"datasets":[{"label":"","data":[1,1],"backgroundColor":["#3B82F6","#3B82F6"],"percentage":[50,50],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["Springer Nature","Elsevier"],"ids":[8,17],"codes":[0,0],"imageUrls":["\/storage\/images\/resized\/voXLqlsvTwv5p3iMQ8Dhs95nqB4AXOG7Taj7G4ra_medium.webp","\/storage\/images\/resized\/GDnYOu1UpMMfMMRV6Aqle4H0YLLsraeD9IP9qScG_medium.webp"],"datasets":[{"label":"","data":[1,1],"backgroundColor":["#3B82F6","#3B82F6"],"percentage":[50,50],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}
Metrics
Cite this
GOST |
RIS |
BibTex
Cite this
GOST
Copy
Dzhivelikian E. et al. Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory // Lecture Notes in Computer Science. 2021. Vol. 12960 LNAI. pp. 13-24.
GOST all authors (up to 50)
Copy
Dzhivelikian E., Latyshev A., Kuderov P., Panov A. Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory // Lecture Notes in Computer Science. 2021. Vol. 12960 LNAI. pp. 13-24.
Cite this
RIS
Copy
TY - GENERIC
DO - 10.1007/978-3-030-86993-9_2
UR - https://doi.org/10.1007%2F978-3-030-86993-9_2
TI - Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory
T2 - Lecture Notes in Computer Science
AU - Dzhivelikian, Evgenii
AU - Latyshev, Artem
AU - Kuderov, Petr
AU - Panov, Aleksandr
PY - 2021
DA - 2021/09/14 00:00:00
PB - Springer Nature
SP - 13-24
VL - 12960 LNAI
SN - 0302-9743
SN - 1611-3349
SN - 1861-2075
SN - 1861-2083
ER -
Cite this
BibTex
Copy
@incollection{2021_Dzhivelikian
author = {Evgenii Dzhivelikian and Artem Latyshev and Petr Kuderov and Aleksandr Panov},
title = {Intrinsic Motivation to Learn Action-State Representation with Hierarchical Temporal Memory},
publisher = {Springer Nature},
year = {2021},
volume = {12960 LNAI},
pages = {13--24},
month = {sep}
}