A Proposal for Reducing the Number of Trial-and-Error Searches for Deep Q-Networks Combined with Exploitation-Oriented Learning

Naoki Kodama, Kazuteru Miyazaki, Taku Harada

研究成果: Conference contribution査読

3 被引用数 (Scopus)

抄録

Deep reinforcement learning has attracted attention for its application in deep Q-networks (DQNs). A DQN can attain superhuman performance, but it requires a large number of trial-and-error searches. To reduce the number of trial-and-error searches required for learning convergence in a DQN, multistep learning can be used and deep Q-networks with profit sharing (DQNwithPS) is one solution, but it has its own set of disadvantages. DQNwithPS optimizes a neural network by learning based on a DQN and profit sharing. However, multistep learning requires proper prefetching parameter tuning, and DQNwithPS has a learning performance degradation problem caused by profit sharing by not considering the expected rewards of a future episode. In this paper, we propose a learning-accelerated DQN combining multistep learning and DQNwithPS to cancel each disadvantage. The proposed method improves the prefetching parameter tuning in multistep learning by DQNwithPS and the learning performance degradation problem in DQNwithPS by multistep learning. By this method, we aim to reduce the number of trial-and-error searches compared to a DQN and DQNwithPS and to realize a manageable fast learning method.

本文言語English
ホスト出版物のタイトルProceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
編集者M. Arif Wani, Moamar Sayed-Mouchaweh, Edwin Lughofer, Joao Gama, Mehmed Kantardzic
出版社Institute of Electrical and Electronics Engineers Inc.
ページ983-988
ページ数6
ISBN(電子版)9781538668047
DOI
出版ステータスPublished - 15 1月 2019
イベント17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018 - Orlando, United States
継続期間: 17 12月 201820 12月 2018

出版物シリーズ

名前Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018

Conference

Conference17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018
国/地域United States
CityOrlando
Period17/12/1820/12/18

フィンガープリント

「A Proposal for Reducing the Number of Trial-and-Error Searches for Deep Q-Networks Combined with Exploitation-Oriented Learning」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル