The Knowledge Sharing Based Reinforcement Learning Algorithm for Collective Behaviors of Mobile Robots


Article Preview

Reinforcement learning algorithm for multi-robot may will become very slow when the number of robots is increasing resulting in an exponential increase of state space. A sequential Q-learning base on knowledge sharing is presented. The rule repository of robots behaviors is firstly initialized in the process of reinforcement learning. Mobile robots obtain present environmental state by sensors. Then the state will be matched to determine if the relevant behavior rule has been stored in database. If the rule is present, an action will be chosen in accordance with the knowledge and the rules, and the matching weight will be refined. Otherwise the new rule will be joined in the database. The robots learn according to a given sequence and share the behavior database. We examine the algorithm by multi-robot following-surrounding behavior, and find that the improved algorithm can effectively accelerate the convergence speed.



Advanced Materials Research (Volumes 588-589)

Edited by:

Lawrence Lim




Y. Song et al., "The Knowledge Sharing Based Reinforcement Learning Algorithm for Collective Behaviors of Mobile Robots", Advanced Materials Research, Vols. 588-589, pp. 1515-1518, 2012

Online since:

November 2012




[1] Y. WANG, C. DESILVA: A machine-learning approach to multi-robot coordination. Engineering Applications of Artificial Intelligence, Vol. 21(2008), p.470.

[2] J. LIU, X. JIN, S. ZHANG: The model and experiment of multi-agent. Beijing: Tsinghua University Press, (2003).

[3] S. GARNIER, J. GAUTRAIS, G. THERAULAZ: The biological principles of swarm intelligence. Swarm Intelligence, Vol. 1(20071), p.3.


[4] M. RIEDMILLER, T. GABEL, R. HAFNER, et al. Reinforcement learning for robot soccer. Autonomous Robots, Vol. 27(2009), p.55.


[5] M. GHAVAMZADEH, S. MAHADEVAN, R. MAKAR: Hierarchical multi-agent reinforcement learning. Autonomous Agents and Multi-Agent Systems, Vol. 13(2006), p.197.


[6] D. B. GU, E. F. YANG: Fuzzy policy reinforcement learning in cooperative multi-robot systems. Journal of Intelligent & Robotic Systems, Vol. 48(2007), p.7.


[7] F. FERNANDEZ, D. BORRAJO, L. E. PARKER: A reinforcement learning algorithm in cooperative multi-robot domains. Journal of Intelligent and Robotic Systems, Vol. 43(2005), p.161.