Abstract
Fully anticipating the overall effect on society is difficult due to the many as-yet-unrecognized factors at disaster sites. There is a need for autonomous disaster relief robots, which can learn from the conditions they encounter and then take independent actions. Reinforcement learning is one way that robots can acquire information about appropriate behavior in new environments. In the present study, we present the results of a disaster relief simulation that included multiple autonomous robots working as a multi-agent system. In order to assist in the use of reinforcement learning for the efficient acquisition of action rules, we divided the task into various sub-tasks. We propose an approach in which cooperative action is obtained by giving each agent a different reward; this encourages the agents to play different roles. We investigated how the various autonomous agents determined the appropriate action rules and examined the influence of providing separate rewards to different agents in the system. We also compared the values of various actions in different learning situations.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, The MIT Press (1998).
Alex V.E. Conradie and Chris Aldrich, Development of neurocontrollers with evolutionary reinforcement learning, Computers & Chemical Engineering, Vol. 30, pp. 1–17 (2005).
C. L. Isbell, C. R. Shelton, M. Kearns, S. Singh, P. Stone, A Social Reinforcement Learning Agent, Proceedings of the Fifth International Conference on Autonomous Agents, pp. 377–384 (2001).
Michael Wooldridge, Intelligent Agents, Multiagent Systems: A modern Approach to Distributed Artificial Intelligence, edited by Gerhard Weiss, The MIT Press (2000).
Peter Stone and Manuela Veloso. Using Machine learning in the Soccer Server, Proc. of IROS-96 Workshop on Robocup (1996).
Kumiko Tanaka-Ishii, Itsuki Noda and Ian Frank et.al, MIKE: An Automatic Commentary System for Soccer – System Design and Control-, Proceedings of International Conference on Multi-Agent Systems’98 (1998).
H. Matsubara, I. Frank and K. Tanaka et.al., Automatic Soccer Commentary and RoboCup, The 2nd Proceedings of RoboCap Workshop (1998).
Pereira, Renato de Pontes/ Engel, Paulo Martins, A Framework for Constrained and Adaptive Behavior-Based Agents, arXiv preprint arXiv:1506.02312v1, pp. 1–16 (2015).
K. Kovac, Simulation of multi-robot reinforcement learning for box-pushing Problem, Proceedings of the 12th IEEE Mediterranean, Vol. 2, pp. 603–606 (2004).
P. Legreneur, M. Laurin and V. Bels, Predator-prey interactions paradigm: a new tool for artificial intelligence, Adaptive Behavior, Vol. 20, pp. 3–9 (2012).
K. C. Jim and C. L. Giles, Talking Helps: Evolving Communicating Agents for the Predator-Prey Pursuit Problem, Artificial Life, No. 6, Vol.3, pp. 237–254 (2000).
L. Panait, and S. Luke, Cooperative Multi-Agent Learning: The state of the Art, Auto Agents Multi-Agent Syst (3), pp. 387–434 (2005).
N. Jennings, K. Sycara, and M. Wooldridge, A roadmap of agent research and development, Autonomous Agents And Multi-Agent Systems, Vol.1, pp. 7–38 (1998).
M. Xie and A. Tachibana, Cooperative Behavior Acquisition for Multi-agent Systems by Q-learning, Proceedings IEEE Symposium on Foundations of Computational Intelligence, 424–428 (2007).
F. Toriumi, H. Yamamoto and I. Okada, Effects of Controllable Facilitators on Social Media: Simulation Analysis Using Generalized Metanorms Games, Proceeding of Web Intelligence and Intelligent Agent Technologies, 2013 IEEE/WIC/ACM international Joint Conferences (2013).
L. Panait, and S. Luke, Cooperative Multi-Agent Learning: The state of the Art, Auto Agents Multi-Agent Syst (3), pp. 387–434 (2005).
Acknowledgments
This research was supported by JSPS KAKENHI Grant Number JP16K01303.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Xie, M., Murata, M., Sato, S. (2017). Acquisition of Cooperative Action by Rescue Agents with Distributed Roles. In: Leu, G., Singh, H., Elsayed, S. (eds) Intelligent and Evolutionary Systems. Proceedings in Adaptation, Learning and Optimization, vol 8. Springer, Cham. https://doi.org/10.1007/978-3-319-49049-6_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-49049-6_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49048-9
Online ISBN: 978-3-319-49049-6
eBook Packages: EngineeringEngineering (R0)