A reinforcement learning system for swarm behaviors

Creators Kuremoto T.

Creators Obayashi M.

Creators Kobayashi K.

Creators Adachi H.

Creators Yoneda K.

IEEE International Joint Conference on IEEE World Congress on Computational Intelligence, Neural Networks, 2008, IJCNN 2008, Hong Kong, 1-8 June 2008.

This paper proposes a neuro-fuzzy system with a reinforcement learning algorithm to realize speedy acquisition of optimal swarm behaviors. The proposed system is constructed with a part of input states classification by the fuzzy net and a part of optimal behavior learning network adopting the actor-critic method. The membership functions and fuzzy rules in the fuzzy net are adaptively formed online by the change of environment states observed in trials of agentpsilas behaviors. The weights of connections between the fuzzy net and the value functions of actor and critic are trained by temporal difference error (TD error). Computer simulations applied to a goal-directed navigation problem using multiple agents were performed Effectiveness of the proposed learning system was confirmed by the simulation results.

Copyright c2008 IEEE. Reprinted from Proceedings of IEEE World Congress on Computational Intelligence, 2008, p. 3710-3715. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of Yamaguchi University Library's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org.()

[ISSN]1098-7576

info:doi/10.1109/IJCNN.2008.4634330

[ISBN]9781424418206

[isVersionOf] [URI]http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=4625775