Open Access
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 typeBook Chapter
Publication date2021-09-14
Quartile SCImago
Q3
Quartile WOS
Impact factor
ISSN03029743, 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, 50%
Brain Informatics
1 publication, 50%
Procedia Computer Science
Procedia Computer Science, 1, 50%
Procedia Computer Science
1 publication, 50%
1

Citations by publishers

1
Springer Nature
Springer Nature, 1, 50%
Springer Nature
1 publication, 50%
Elsevier
Elsevier, 1, 50%
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.
Metrics
Share
Cite this
GOST |
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.
RIS |
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 -
BibTex
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}
}
Found error?