EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring Deep Reinforcement Learning with Multi Q-Learning

Ethan Duryea, Michael Ganger, Wei Hu

Intelligent Control and Automation · 2016 · 07 (04) · 129-144

DOI: 10.4236/ica.2016.74012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Intelligent Control and Automation, 2016. Verfasst von Ethan Duryea und 2 weiteren Autor:innen. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Q-learning is a popular temporal-difference reinforcement learning algorithm which often explicitly stores state values using lookup tables. This implementation has been proven to converge to the optimal solution, but it is often beneficial to use a function-approximation system, such as deep neural networks, to estimate state values. It has been previously observed that Q-learning can be unstable when using value function approximation or when operating in a stochastic environment. This instability can adversely affect the algorithm’s ability to maximize its returns. In this paper, we present a new algorithm called Multi Q-learning to attempt to overcome the instability seen in Q-learning. We test our algorithm on a 4 × 4 grid-world with different stochastic reward functions using various deep neural networks and convolutional networks. Our results show that in most cases, Multi Q-learning outperforms Q-learning, achieving average returns up to 2.5 times higher than Q-learning and having a standard deviation of state values as low as 0.58.

Zitieren

APA

Duryea, E., Ganger, M., & Hu, W. (2016). Exploring Deep Reinforcement Learning with Multi Q-Learning. Intelligent Control and Automation, 07(04), 129-144. https://doi.org/10.4236/ica.2016.74012

Vancouver

Duryea E, Ganger M, Hu W. Exploring Deep Reinforcement Learning with Multi Q-Learning. Intelligent Control and Automation. 2016;07(04):129-144. doi:10.4236/ica.2016.74012

BibTeX
@article{Duryea2016,
  author = {Duryea, Ethan and Ganger, Michael and Hu, Wei},
  title = {Exploring Deep Reinforcement Learning with Multi Q-Learning},
  journal = {Intelligent Control and Automation},
  year = {2016},
  volume = {07},
  number = {04},
  pages = {129--144},
  doi = {10.4236/ica.2016.74012}
}
Kostenlos starten →