Deep Neural Networks and Experience Replay in Q-learning Extensions: A Review
International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · 2025-06 · 33 (04) · 401-432
DOI: 10.1142/s0218488525500175 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, online erschienen am 23.06.2025. Verfasst von Richard Sakyi Osei und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 120 Literaturangaben.
Abstract (Originalsprache)
Reinforcement Learning (RL) is a type of machine learning where actions are learned and taken to solve sequential decision problems. There have been several extensions in the Q-learning algorithm, but more extensions have occurred since the breakthrough of the Deep Q-network algorithm. We study the two pivotal aspects of the DQN algorithm (deep neural network and experience replay) and other related extensions; we focus on experience replay. Our study identifies multiple extensions in network structure, experience sampling strategies, memory managing techniques, and memory structures. We further indicate the extended algorithms’ strengths and weaknesses and suggest future works.
Zitieren
APA
Osei, R. S., & Lopez, D. (2025). Deep Neural Networks and Experience Replay in Q-learning Extensions: A Review. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 33(04), 401-432. https://doi.org/10.1142/s0218488525500175
Vancouver
Osei RS, Lopez D. Deep Neural Networks and Experience Replay in Q-learning Extensions: A Review. International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. 2025;33(04):401-432. doi:10.1142/s0218488525500175
BibTeX
@article{Osei2025,
author = {Osei, Richard Sakyi and Lopez, Daphne},
title = {Deep Neural Networks and Experience Replay in Q-learning Extensions: A Review},
journal = {International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems},
year = {2025},
volume = {33},
number = {04},
pages = {401--432},
doi = {10.1142/s0218488525500175}
}
EUVIMED