Salvato in:
Dettagli Bibliografici
Autori principali: Sabry, Mohammed, Khalifa, Amr M. A.
Natura: Preprint
Pubblicazione: 2019
Soggetti:
Accesso online:https://arxiv.org/abs/1910.05983
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929312543801344
author Sabry, Mohammed
Khalifa, Amr M. A.
author_facet Sabry, Mohammed
Khalifa, Amr M. A.
contents The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We also present experiments conducted on benchmark environments, demonstrating the effectiveness of our methodology in enhancing stability and reducing both variance and overestimation in model performance.
format Preprint
id arxiv_https___arxiv_org_abs_1910_05983
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle On the Reduction of Variance and Overestimation of Deep Q-Learning
Sabry, Mohammed
Khalifa, Amr M. A.
Machine Learning
The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestimation phenomena. In this paper, we examine new methodology to solve these issues, we propose using Dropout techniques on deep Q-Learning algorithm as a way to reduce variance and overestimation. We also present experiments conducted on benchmark environments, demonstrating the effectiveness of our methodology in enhancing stability and reducing both variance and overestimation in model performance.
title On the Reduction of Variance and Overestimation of Deep Q-Learning
topic Machine Learning
url https://arxiv.org/abs/1910.05983