Have a personal or library account? Click to login
An Active Exploration Method for Data Efficient Reinforcement Learning Cover

An Active Exploration Method for Data Efficient Reinforcement Learning

International Journal of Applied Mathematics and Computer Science
Volume 29 (2019): Issue 2 (June 2019)
By: Dongfang Zhao,  Jiafeng Liu,  Rui Wu,  Dansong Cheng and  Xianglong Tang  
Open Access
|Jul 2019

Authors

Dongfang Zhao

School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Jiafeng Liu

School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Rui Wu

School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Dansong Cheng

cdsinhit@hit.edu.cn

School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China

Xianglong Tang

School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
DOI: https://doi.org/10.2478/amcs-2019-0026 | Journal eISSN: 2083-8492 | Journal ISSN: 1641-876X
Journal RSS Feed
Language: English
Page range: 351 - 362
Submitted on: Jul 18, 2018
Accepted on: Jan 31, 2019
Published on: Jul 4, 2019
Published by: University of Zielona Góra
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year
Keywords:
reinforcement learning,
information entropy,
PILCO,
data efficiency
Related subjects:
Mathematics,
Applied mathematics

© 2019 Dongfang Zhao, Jiafeng Liu, Rui Wu, Dansong Cheng, Xianglong Tang, published by University of Zielona Góra
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 29 (2019): Issue 2 (June 2019)Next article