Title: An Experimental Study for Exploration-oriented Behavior in Maze-solving using Reinforcement Learning based on Communication Protocol

Issue Number: Vol. 9, No. 2
Year of Publication: 2019
Page Numbers: 31-37
Authors: Masashi SUGIMOTO, Shunsuke INADA, Haruka MATSUFUJI, Shiro URUSHIHARA, Kazunori HOSOTANI, Manabu KATO, Hitoshi SORI, Shinji TSUZUKI, Hiroyuki INOUE
Journal Name: International Journal of New Computer Architectures and their Applications (IJNCAA)
- Hong Kong
DOI:  http://dx.doi.org/10.17781/P002612


In this study, the reinforcement learning agent under the situation of communicable as multi-agent system will be improved efficiency. In reinforcement learning, this method will be supposed that agent is able to observe the environment, completely. However, there is a limit on the information of the sensors. Moreover, it is hard to learn the reinforcement learning agent in the actual environment cause of some noise of actual environment or source device. In addition, a time per a episode will enlarge because an agent will be explored in a given area. In this study, the proposed method has been using two type agents that communicate as information exchange on the location to settle this problem moreover, the noise will be mixed with knowledge space in the situation of the knowledge sharing. In addition, sometimes the any information won’t be transmitted in the situation of knowledge sharing. Thus, the self-decision mechanism will be installed. From this viewpoint, in this study aims to improve maze-solving technique, efficiency by which to the multi-agent reinforcement learning’s agents under the situation. As a result, the proposed method has been confirmed that is provided suitable solution for an approach to the goal for the agents.