Welcome to the InfoSci Platform
Deep Reinforcement Learning and In-Network Caching-Based Martial Arts Physical Training

Deep Reinforcement Learning and In-Network Caching-Based Martial Arts Physical Training

Qi Zhang
Copyright: © 2022 |Volume: 13 |Issue: 2 |Pages: 8
ISSN: 1947-3532|EISSN: 1947-3540|EISBN13: 9781683181828|DOI: 10.4018/IJDST.291079
Cite Article Cite Article

MLA

Zhang, Qi. "Deep Reinforcement Learning and In-Network Caching-Based Martial Arts Physical Training." IJDST vol.13, no.2 2022: pp.1-8. http://doi.org/10.4018/IJDST.291079

APA

Zhang, Q. (2022). Deep Reinforcement Learning and In-Network Caching-Based Martial Arts Physical Training. International Journal of Distributed Systems and Technologies (IJDST), 13(2), 1-8. http://doi.org/10.4018/IJDST.291079

Chicago

Zhang, Qi. "Deep Reinforcement Learning and In-Network Caching-Based Martial Arts Physical Training," International Journal of Distributed Systems and Technologies (IJDST) 13, no.2: 1-8. http://doi.org/10.4018/IJDST.291079

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

The martial arts have been regarded as the athletics project at the international competitions, and the corresponding physical training has also brought about widespread attention. However, the traditional physical training evaluation methods are usually performed in the offline way and they are very difficult to achieve the large-scale data evaluation with the high evaluation efficiency. Therefore, this paper leverages Deep Reinforcement Learning (DRL) and in-network caching to realize the high-precision and high-efficiency data evaluation under the large-scale martial arts physical training environment while guarantees the online performance evaluation. Meanwhile, Q-learning based DRL is used to make the large-scale data evaluation. In addition, a communication protocol based on in-network caching is proposed to support the online function. The comparison experiments demonstrate that the proposed conduction method for the martial arts physical training is more efficient than the benchmark.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.