Multi-agent Coordination using Reinforcement Learning with a Relay Agent

Wiem Zemzem, Moncef Tagina

Abstract

This paper focuses on distributed reinforcement learning in cooperative multi-agent systems, where several simultaneously and independently acting agents have to perform a common foraging task. To do that, a novel cooperative action selection strategy and a new kind of agents, called "relay agent", are proposed. The conducted simulation tests indicate that our proposals improve coordination between learners and are extremely efficient in terms of cooperation in large, unknown and stationary environments.

References

  1. Bruno C. Da Silva, Eduardo W. Basso, Ana L. C. Bazzan, P. M. E. (2006). Dealing with non-stationary environments using context detection. In the 23rd International Conference on Machine Learning, pages 217- 224. ACM Press.
  2. Coggan, M. (2004). Exploration and exploitation in reinforcement learning. Research supervised by Prof. Doina Precup, CRA-W DMP Project at McGill University.
  3. Cunningham, B. and Cao, Y. (2012). Non-reciprocating Sharing Methods in Cooperative Q-Learning Environments. In 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, pages 212-219. IEEE.
  4. Guo, H. and Meng, Y. (2010). Distributed Reinforcement Learning for Coordinate Multi-Robot Foraging. Journal of Intelligent and Robotic Systems, 60(3-4):531- 551.
  5. Hugues, L. and Bredeche, N. (2006). Simbad: An Autonomous Robot Simulation Package for Education and Research. In International Conference on Simulation of Adaptive Behavior, volume 4095, pages 831- 842. Springer Berlin Heidelberg.
  6. Partalas, I., Feneris, I., and Vlahavas, I. (2008). A hybrid multiagent reinforcement learning approach using strategies and fusion. International Journal on Artificial Intelligence Tools, 17(05):945-962.
  7. Tan, M. (1997). Multi-agent reinforcement learning: independent vs. cooperative agents. In the tenth international conference on machine learning, pages 330- 337. Morgan Kaufmann Publishers Inc.
  8. Torrey, L. and Taylor, M. E. (2012). Help an agent out: Student/teacher learning in sequential decision tasks. In Proceedings of the Adaptive and Learning Agents Workshop 2012, ALA 2012 - Held in Conjunction with the 11th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2012, pages 41-48.
  9. Zemzem, W. and Tagina, M. (2015). Cooperative multiagent learning in a large dynamic environment. In Lecture Notes in Computer Science, chapter MDAI, pages 155-166. Springer.
Download


Paper Citation


in Harvard Style

Zemzem W. and Tagina M. (2017). Multi-agent Coordination using Reinforcement Learning with a Relay Agent . In Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-247-9, pages 537-545. DOI: 10.5220/0006327305370545


in Bibtex Style

@conference{iceis17,
author={Wiem Zemzem and Moncef Tagina},
title={Multi-agent Coordination using Reinforcement Learning with a Relay Agent},
booktitle={Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2017},
pages={537-545},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006327305370545},
isbn={978-989-758-247-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Multi-agent Coordination using Reinforcement Learning with a Relay Agent
SN - 978-989-758-247-9
AU - Zemzem W.
AU - Tagina M.
PY - 2017
SP - 537
EP - 545
DO - 10.5220/0006327305370545