Elsevier
Cognitive Systems Research
,  том 65 ,  страницы 74-78

Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft

Тип публикации: Journal Article
Дата публикации: 2021-01-01
Elsevier
scimago Q2
wos Q2
БС1
SJR: 0.604
CiteScore: 6.1
Impact factor: 2.4
ISSN: 13890417, 22144366
Artificial Intelligence
Software
Experimental and Cognitive Psychology
Cognitive Neuroscience
Краткое описание
We present Hierarchical Deep Q-Network (HDQfD) that won first place in the MineRL competition. The HDQfD works on imperfect demonstrations and utilizes the hierarchical structure of expert trajectories. We introduce the procedure of extracting an effective sequence of meta-actions and subgoals from the demonstration data. We present a structured task-dependent replay buffer and an adaptive prioritizing technique that allow the HDQfD agent to gradually erase poor-quality expert data from the buffer. In this paper, we present the details of the HDQfD algorithm and give the experimental results in the Minecraft domain.
Найдено 
Найдено 

Топ-30

Журналы

1
2
3
4
Lecture Notes in Computer Science
Lecture Notes in Computer Science, 4, 25%
Lecture Notes in Computer Science
4 публикации, 25%
Lecture Notes in Networks and Systems
Lecture Notes in Networks and Systems, 2, 12.5%
Lecture Notes in Networks and Systems
2 публикации, 12.5%
Studies in Computational Intelligence
Studies in Computational Intelligence, 1, 6.25%
Studies in Computational Intelligence
1 публикация, 6.25%
Scientific Programming
Scientific Programming, 1, 6.25%
Scientific Programming
1 публикация, 6.25%
Computational Intelligence and Neuroscience
Computational Intelligence and Neuroscience, 1, 6.25%
Computational Intelligence and Neuroscience
1 публикация, 6.25%
Pattern Recognition and Image Analysis
Pattern Recognition and Image Analysis, 1, 6.25%
Pattern Recognition and Image Analysis
1 публикация, 6.25%
Neural Processing Letters
Neural Processing Letters, 1, 6.25%
Neural Processing Letters
1 публикация, 6.25%
Scientific and Technical Information Processing
Scientific and Technical Information Processing, 1, 6.25%
Scientific and Technical Information Processing
1 публикация, 6.25%
1
2
3
4

Издатели

1
2
3
4
5
6
7
8
Springer Nature
Springer Nature, 8, 50%
Springer Nature
8 публикаций, 50%
Institute of Electrical and Electronics Engineers (IEEE)
Institute of Electrical and Electronics Engineers (IEEE), 4, 25%
Institute of Electrical and Electronics Engineers (IEEE)
4 публикации, 25%
Hindawi Limited
Hindawi Limited, 2, 12.5%
Hindawi Limited
2 публикации, 12.5%
Pleiades Publishing
Pleiades Publishing, 1, 6.25%
Pleiades Publishing
1 публикация, 6.25%
Allerton Press, 1, 6.25%
Allerton Press
1 публикация, 6.25%
1
2
3
4
5
6
7
8
  • Мы не учитываем публикации, у которых нет DOI.
  • Статистика публикаций обновляется еженедельно.

Вы ученый?

Создайте профиль, чтобы получать персональные рекомендации коллег, конференций и новых статей.
Метрики
16
Поделиться
Цитировать
ГОСТ |
Цитировать
ГОСТ Скопировать
Skrynnik A. et al. Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft // Cognitive Systems Research. 2021. Vol. 65. pp. 74-78.
ГОСТ со всеми авторами (до 50) Скопировать
Skrynnik A., Staroverov A., Aitygulov E., Aksenov K., Davydov V., Panov A. Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft // Cognitive Systems Research. 2021. Vol. 65. pp. 74-78.
RIS |
Цитировать
RIS Скопировать
TY - JOUR
DO - 10.1016/j.cogsys.2020.08.012
UR - https://doi.org/10.1016/j.cogsys.2020.08.012
TI - Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft
T2 - Cognitive Systems Research
AU - Skrynnik, Alexey
AU - Staroverov, Aleksei
AU - Aitygulov, Ermek
AU - Aksenov, Kirill
AU - Davydov, Vasilii
AU - Panov, Aleksandr
PY - 2021
DA - 2021/01/01
PB - Elsevier
SP - 74-78
VL - 65
SN - 1389-0417
SN - 2214-4366
ER -
BibTex
Цитировать
BibTex (до 50 авторов) Скопировать
@article{2021_Skrynnik,
author = {Alexey Skrynnik and Aleksei Staroverov and Ermek Aitygulov and Kirill Aksenov and Vasilii Davydov and Aleksandr Panov},
title = {Hierarchical Deep Q-Network from imperfect demonstrations in Minecraft},
journal = {Cognitive Systems Research},
year = {2021},
volume = {65},
publisher = {Elsevier},
month = {jan},
url = {https://doi.org/10.1016/j.cogsys.2020.08.012},
pages = {74--78},
doi = {10.1016/j.cogsys.2020.08.012}
}