Presentation | 2014-03-06 Distributed Reinforcement Learning for Priority-based Data Transmission in Delay Tolerant Networks Shin'ichiro MURATA, Takuji TACHIBANA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In Fukui prefecture, in order to revitalize regional communities, regional information and event information are distributed to local residents and visitors. It is expected that such an information distribution can enhance regional activation. Therefore, we consider the utilization of delay tolerant network technology to distribute such as information to passengers who are in an urban area. Especially in this paper, in order to distribute high priority data and low priority data, we propose a method based on distributed reinforcement learning, which is implemented in user's mobile terminal. In this method, a map is divided into segments, and each agent learns the optimal action in each segment. By using the proposed method, each user can distribute high priority data more aggressively than low priority data in a particular area. Moreover, by utilizing the past information, high priority data and low priority data are transmitted effectively in the particular area. We evaluate the performance of the proposed method with simulation. In numerical examples, we investigate the effectiveness of our proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Distributed reinforcement learning / Q-learning / Delay Tolerant Networks / Priority / Information Distribution |
Paper # | NS2013-191 |
Date of Issue |
Conference Information | |
Committee | NS |
---|---|
Conference Date | 2014/2/27(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Network Systems(NS) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Distributed Reinforcement Learning for Priority-based Data Transmission in Delay Tolerant Networks |
Sub Title (in English) | |
Keyword(1) | Distributed reinforcement learning |
Keyword(2) | Q-learning |
Keyword(3) | Delay Tolerant Networks |
Keyword(4) | Priority |
Keyword(5) | Information Distribution |
1st Author's Name | Shin'ichiro MURATA |
1st Author's Affiliation | Graduate School of Engineering, University of Fukui() |
2nd Author's Name | Takuji TACHIBANA |
2nd Author's Affiliation | Graduate School of Engineering, University of Fukui |
Date | 2014-03-06 |
Paper # | NS2013-191 |
Volume (vol) | vol.113 |
Number (no) | 472 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |