IDEAS home Printed from https://ideas.repec.org/a/hin/jnlmpe/2129393.html
   My bibliography  Save this article

Ensemble Network Architecture for Deep Reinforcement Learning

Author

Listed:
  • Xi-liang Chen
  • Lei Cao
  • Chen-xi Li
  • Zhi-xiong Xu
  • Jun Lai

Abstract

The popular deep learning algorithm is known to be instability because of the -value’s shake and overestimation action values under certain conditions. These issues tend to adversely affect their performance. In this paper, we develop the ensemble network architecture for deep reinforcement learning which is based on value function approximation. The temporal ensemble stabilizes the training process by reducing the variance of target approximation error and the ensemble of target values reduces the overestimate and makes better performance by estimating more accurate -value. Our results show that this architecture leads to statistically significant better value evaluation and more stable and better performance on several classical control tasks at OpenAI Gym environment.

Suggested Citation

  • Xi-liang Chen & Lei Cao & Chen-xi Li & Zhi-xiong Xu & Jun Lai, 2018. "Ensemble Network Architecture for Deep Reinforcement Learning," Mathematical Problems in Engineering, Hindawi, vol. 2018, pages 1-6, April.
    • Handle: RePEc:hin:jnlmpe:2129393
    DOI: 10.1155/2018/2129393
    as

    Download full text from publisher

    File URL: http://downloads.hindawi.com/journals/MPE/2018/2129393.pdf
    Download Restriction: no
    File URL: http://downloads.hindawi.com/journals/MPE/2018/2129393.xml
    Download Restriction: no
    File URL: https://libkey.io/10.1155/2018/2129393?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Lu, Jing & Meng, Yucan & Timmermans, Harry & Zhang, Anming, 2021. "Modeling hesitancy in airport choice: A comparison of discrete choice and machine learning methods," Transportation Research Part A: Policy and Practice, Elsevier, vol. 147(C), pages 230-250.
    2. Sun, Fangyuan & Kong, Xiangyu & Wu, Jianzhong & Gao, Bixuan & Chen, Ke & Lu, Ning, 2022. "DSM pricing method based on A3C and LSTM under cloud-edge environment," Applied Energy, Elsevier, vol. 315(C).
    3. Pinciroli, Luca & Baraldi, Piero & Ballabio, Guido & Compare, Michele & Zio, Enrico, 2022. "Optimization of the Operation and Maintenance of renewable energy systems by Deep Reinforcement Learning," Renewable Energy, Elsevier, vol. 183(C), pages 752-763.
    4. Hao, Zhaojun & Di Maio, Francesco & Zio, Enrico, 2023. "A sequential decision problem formulation and deep reinforcement learning solution of the optimization of O&M of cyber-physical energy systems (CPESs) for reliable and safe power production and supply," Reliability Engineering and System Safety, Elsevier, vol. 235(C).
    5. Raad Khraishi & Ramin Okhrati, 2022. "Offline Deep Reinforcement Learning for Dynamic Pricing of Consumer Credit," Papers 2203.03003, arXiv.org.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hin:jnlmpe:2129393. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Mohamed Abdelhakeem (email available below). General contact details of provider: https://www.hindawi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.