TY - GEN
T1 - A study of reinforcement learning with knowledge sharing - Applications to real mobile robots
AU - Ito, Kazuyuki
AU - Imoto, Yoshiaki
AU - Taguchi, Hideaki
AU - Gofuku, Akio
PY - 2004/12/1
Y1 - 2004/12/1
N2 - In this paper, we consider multi-agent system in which every agents have own tasks that differs each other. We propose a method that decreases learning time of reinforcement learning by using the model of environment. In the proposed algorithm, the model is created by sharing the experiences of agents each other. To demonstrate the effectiveness of the proposed method, simulations of a puddle world and experiments of a maze world have been carried out. As a result effective behaviors have been obtained quickly.
AB - In this paper, we consider multi-agent system in which every agents have own tasks that differs each other. We propose a method that decreases learning time of reinforcement learning by using the model of environment. In the proposed algorithm, the model is created by sharing the experiences of agents each other. To demonstrate the effectiveness of the proposed method, simulations of a puddle world and experiments of a maze world have been carried out. As a result effective behaviors have been obtained quickly.
UR - http://www.scopus.com/inward/record.url?scp=28344436787&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=28344436787&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:28344436787
SN - 0780386418
T3 - Proceedings - 2004 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2004
SP - 175
EP - 180
BT - Proceedings - 2004 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2004
T2 - Proceedings - 2004 IEEE International Conference on Robotics and Biomimetics, IEEE ROBIO 2004
Y2 - 22 August 2004 through 26 August 2004
ER -