Open Access
Open access
Brain Informatics, volume 9, issue 1, publication number 8

Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments

Publication typeJournal Article
Publication date2022-04-02
Quartile SCImago
Q1
Quartile WOS
Impact factor
ISSN21984018, 21984026
Computer Science Applications
Neurology
Cognitive Neuroscience
Abstract

Biologically plausible models of learning may provide a crucial insight for building autonomous intelligent agents capable of performing a wide range of tasks. In this work, we propose a hierarchical model of an agent operating in an unfamiliar environment driven by a reinforcement signal. We use temporal memory to learn sparse distributed representation of state–actions and the basal ganglia model to learn effective action policy on different levels of abstraction. The learned model of the environment is utilized to generate an intrinsic motivation signal, which drives the agent in the absence of the extrinsic signal, and through acting in imagination, which we call dreaming. We demonstrate that the proposed architecture enables an agent to effectively reach goals in grid environments.

Citations by journals

1
Procedia Computer Science
Procedia Computer Science, 1, 16.67%
Procedia Computer Science
1 publication, 16.67%
Sensors
Sensors, 1, 16.67%
Sensors
1 publication, 16.67%
Neural Networks
Neural Networks, 1, 16.67%
Neural Networks
1 publication, 16.67%
Pattern Recognition and Image Analysis
Pattern Recognition and Image Analysis, 1, 16.67%
Pattern Recognition and Image Analysis
1 publication, 16.67%
Optical Memory and Neural Networks (Information Optics)
Optical Memory and Neural Networks (Information Optics), 1, 16.67%
Optical Memory and Neural Networks (Information Optics)
1 publication, 16.67%
Lecture Notes in Computer Science
Lecture Notes in Computer Science, 1, 16.67%
Lecture Notes in Computer Science
1 publication, 16.67%
1

Citations by publishers

1
2
Elsevier
Elsevier, 2, 33.33%
Elsevier
2 publications, 33.33%
Pleiades Publishing
Pleiades Publishing, 2, 33.33%
Pleiades Publishing
2 publications, 33.33%
Multidisciplinary Digital Publishing Institute (MDPI)
Multidisciplinary Digital Publishing Institute (MDPI), 1, 16.67%
Multidisciplinary Digital Publishing Institute (MDPI)
1 publication, 16.67%
Springer Nature
Springer Nature, 1, 16.67%
Springer Nature
1 publication, 16.67%
1
2
  • 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. Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments // Brain Informatics. 2022. Vol. 9. No. 1. 8
GOST all authors (up to 50) Copy
Dzhivelikian E., Latyshev A., Kuderov P., Panov A. I. Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments // Brain Informatics. 2022. Vol. 9. No. 1. 8
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1186/s40708-022-00156-6
UR - https://doi.org/10.1186%2Fs40708-022-00156-6
TI - Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments
T2 - Brain Informatics
AU - Kuderov, Petr
AU - Panov, Aleksandr I
AU - Dzhivelikian, Evgenii
AU - Latyshev, Artem
PY - 2022
DA - 2022/04/02 00:00:00
PB - Springer Nature
IS - 1
VL - 9
PMID - 35366128
SN - 2198-4018
SN - 2198-4026
ER -
BibTex
Cite this
BibTex Copy
@article{2022_Dzhivelikian,
author = {Petr Kuderov and Aleksandr I Panov and Evgenii Dzhivelikian and Artem Latyshev},
title = {Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments},
journal = {Brain Informatics},
year = {2022},
volume = {9},
publisher = {Springer Nature},
month = {apr},
url = {https://doi.org/10.1186%2Fs40708-022-00156-6},
number = {1},
doi = {10.1186/s40708-022-00156-6}
}
Found error?