International Journal of

Soft Computing and Software Engineering [JSCSE]

ISSN: 2251-7545

Prefix DOI : 10.7321/jscse

URL: http://JSCSE.com

A Peer-Reviewed Journal

The International Journal of

Soft Computing and Software Engineering [JSCSE]

UserName:

Password:

Publication Year:

[ 2011 ] [ 2012 ] [ 2013 ] [ 2014 ] [ 2015 ] [ 2016 ] [ 2017 ]

[Vol. 3, No.1, Jan] [Vol. 3, No.2, Feb] [Vol. 3, No.3, Mar] [Vol. 3, No.4, Apr] [Vol. 3, No.5, May] [Vol. 3, No.6, Jun] [Vol. 3, No.7, Jul] [Vol. 3, No.8, Aug] [Vol. 3, No.9, Sep] [Vol. 3, No.10, Oct] [Vol. 3, No.11, Nov] [Vol. 3, No.12, Dec]

Advance Search
Table of Contents [Vol. 3, No.2, Feb]

Use of the knowledge of Perceptual State Transition in Reinforcement Learning

Kentarou Kurashige, Yoshiki Miyazaki
Doi : 10.7321/jscse.v3.n2.1
Page : 1 - 12

Show Summary

Abstract . Reinforcement learning(RL) is one of machine learning and is often used for actual robot. A reward which indicates a task for robot is most important information on RL. But a way to get a reward will change in multiple tasks. It makes performance of RL to be worse. To overcome this problem, we focus on environmental information. The knowledge on RL is based on reward, so it will be useless when given task changes. The opposite to it, environmental information is independent to reward. It does not chanse and is useful after given task changed and new task was given. In this paper, we suggest the method to acquire environmental state transition through sensors as perceptual state transition and to use it to adapt for new task quickly. In addition to that, we suggest that the method updates its stored knowledge every sensing. We consider the method adapt for change of environment by this update. Using proposed method, a robot can learn effectively for multiple task and dynamic environment. In this paper, we perform two kinds of experiments with simulation. One is for multiple tasks under a static environment and another is for a task under a dynamic environment. We will show the validity of proposed system by these simulations.
Keyword : reinforcement learning; multi-tasks; environmental knowledge; dynamic environment

Cloud Template, a Big Data Solution

Mehdi Bahrami
Doi : 10.7321/jscse.v3.n2.2
Page : 13 - 17

Show Summary

Abstract . Today the emerging field of cloud computing has become as a new concept for hosting and delivering different services over the Internet and network for dealing with big data issues. Cloud computing is attractive to different business owners of both small and corporations as it eliminates the requirement for end-users to plan ahead for provisioning a massive and expensive infrastructures, and allows corporations to start with low investment and increase resources on demand. Despite the fact that cloud computing offers huge opportunities to the both in-house IT and out-house IT industry, the development of cloud computing technology is currently has several issues, such as lack of customization. This study presents an idea for introducing concept of “Cloud Templates” which will be used for analyzing, designing, developing and implementing cloud computing systems. We present a template based design for cloud computing systems, highlighting its key concepts, architectural principles and state-of-the-art implementation requirements, as well as research challenges and future work requirements. The aim of this idea is to provide a concept for important area of big data.
Keyword : Software Architecture, Cloud Computing, Software Template, Big Data