Distributed Deep Reinforcement Learning Method Using Profit Sharing for Learning Acceleration-Reference-Cited by-同舟云学术

Distributed Deep Reinforcement Learning Method Using Profit Sharing for Learning Acceleration

Published:2020-06-27 Issue:8 Volume:15 Page:1188-1196
ISSN:1931-4973
Container-title:IEEJ Transactions on Electrical and Electronic Engineering
language:en
Short-container-title:IEEJ Trans Elec Electron Eng

Author:

Kodama Naoki¹,Harada Taku²,Miyazaki Kazuteru³

Affiliation:

1. Department of Industrial Administration, Graduate School of Science and TechnologyTokyo University of Science 2641 Yamazaki, Noda‐shi, Chiba 278‐8510 Japan

2. Department of Industrial Administration, Faculty of Science and TechnologyTokyo University of Science 2641 Yamazaki, Noda‐shi, Chiba 278‐8510 Japan

3. Research Department, National Institution of Academic Degrees and Quality Enhancement of Higher Education 1‐29‐1 Gakuen‐nishimachi, Kodaira‐shi, Tokyo 187‐8587 Japan

Publisher

Wiley

Subject

Electrical and Electronic Engineering

Link

https://onlinelibrary.wiley.com/doi/pdf/10.1002/tee.23180

Reference23 articles.

1. Playing Atari with deep reinforcement learning;Mnih V;NIPS Deep Learning Workshop 2013,2013

2. Human-level control through deep reinforcement learning

3. Q-learning

4. Self-improving reactive agents based on reinforcement learning, planning and teaching

5. BellemareMG NaddafY VenessJ BowlingM. The Arcade learning environment: An evaluation platform for general agents arXiv preprint arXiv:1207.4708;2012

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Home Energy Management Algorithm Based on Deep Reinforcement Learning Using Multistep Prediction;IEEE Access;2021