Multiactor approach and hexapod robot learning

Proceedings of IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA

Volumn , Issue , 2005, Pages 665-671

  Zennir, Youcef ^a   Couturier, Pierre ^b  

^a ECOLE CENTRALE DE LILLE   (France)

^b ECOLE DES MINES D ALÈS   (France)

Author keywords

Hexapod robot; Posture control; Q multiactor; Reinforcement learning

Indexed keywords

COMPUTER SIMULATION; LEARNING SYSTEMS; MOTION CONTROL; PROBLEM SOLVING; TRAJECTORIES;

HEXAPOD ROBOT; POSTURE CONTROL; Q-MULTIACTOR; REINFORCEMENT LEARNING;

INDUSTRIAL ROBOTS;

EID: 28444453633     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. C. Claus, and C. Boutillier, " The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems," AAAI, pp.746-752, 1998.
2. R. A. Brooks A, "Robot that walks; emergent behaviors from a carefully evolved network," Neural computation, pp.365-382, 1989.
3. E. Celaya, and J.M. Porta, "A Control Structure for the locomotion of a legged Robot on difficult Terrain," IEEE Robotics and Automation Magazine, vol. 5, no. 2, pp.43-51, 1998.
4. D.Graham, "Pattern and control of walking in insects," Advances in insect physiology, vol.18, pp.31-140, 1985.
5. J. Hu, and M. P. Wellman, "Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm," 15th International Conference on Machine Learning, in Madison, Wisconsin, USA, pp.242-250, 1998.
6. D.A.Kingsley, R. D.Quinn, and R. E.Ritzmann, "A cockroach inspired robot with artificial muscles," International Symposium on Adaptive Motion of Animals and Machines, Kyoto, Japan, 7 p, 2003.
7. F.Kirchner, "Q-learning of complex behaviours on a six-legged walking machine," Robotics and autonomous systems, pp.253-262, 1998.
8. M. L.Littman, "Value-function reinforceùment learning in Markov games," Journal of cognitive Systems Research 2, Elsevier, pp. 55-66, 2001.
9. M.J.Randall, "Stable adaptive neural control of systems with closed kinematic chains applied to biologically-inspired walking robots," These in philosophy. Bristol: Faculty of engineering, University of the West of England, Bristol, 322 p, 1999.
10. S.Sehad, "Contribution à l'étude et au développement de modèles connexionnistes à apprentissage par renforcement: application à l'acquisition de comportements adaptatifs," Thèse de génie informatique et traitement du signal. Montpellier: Université de Montpellier II, 112 p, 1996.
11. R.S.Sutton and A.G.Barto, "Reinforcement Learning," Mit press, Cambridge, Bradford book, 322 p, 1998. ISBN 0-262-19398-1.
12. th International conference on control and automation, IEEE Control chapter, Singapore, Montreal section, Montréal, Canada, pp. 896-900, 2003. ISBN / 0-7803-7777-X(CD-ROM).
13. th International Conference on Machine Learning, in Madison, Wisconsin, USA, pp.242-250, 1998.