Learning in large cooperative multi-robot domains

International Journal of Robotics Research

Volumn 16, Issue 4, 1997, Pages 217-226

  Fernandez F ^a,b   Parker, L E ^a  

^a OAK RIDGE NATIONAL LABORATORY   (United States)

^b UNIVERSIDAD CARLOS III DE MADRID   (Spain)

Author keywords

Cooperative robotics; Multi robot systems; Reinforcement learning; State space representation

Indexed keywords

ARTIFICIAL INTELLIGENCE; LEARNING ALGORITHMS; MATHEMATICAL MODELS; MOTION CONTROL; ROBOT LEARNING; STATE SPACE METHODS; VECTOR QUANTIZATION;

COOPERATIVE MULTI-ROBOT DOMAINS; COOPERATIVE ROBOTICS; REINFORCEMENT LEARNING; STATE-SPACE REPRESENTATION;

ROBOTICS;

EID: 5644261272     PISSN: 02783649     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (28)

1. G. Weiss & S. Sen (Eds.), Adaption and learning in multi-agent systems (Berlin: Springer, 1996).
2. L. Kaelbling, M.L. Littman, & A.W. Moore, Reinforcement learning: A survey, Journal of Artificial Intelligence Research, 4, 1996, 237-285.
3. A.W. Moore, Variable resolution dynamic programming: Efficiently learning action maps in multivariate real-valued spaces, Proc. 8th Int. Conf. on Machine Learning, Evanston, IL, 1991, 333-337.
4. R. Munos & A. Moore, Variable resolution discretization for high-accuracy solutions of optimal control problems, Proc. 16th Int. Joint Conf. on Artificial Intelligence, 2, Stockholm, Sweden, 1999, 1348-1355.
5. D. Chapman & L.P. Kaelbling, Input generalization in delayed reinforcement learning: An algorithm and performance comparisons, Proc. Int. Joint Conf. on Artificial Intelligence, Sydney, Australia, 1991, 726-731.
6. M. Asada, S. Noda, & K. Hosoda, Action-based sensor space categorization for robot learning, Proc. 1996 IEEE/RSJ Int. Conf. on Intelligence Robots and Systems (IROS'96), 3, Osaka, Japan, 1996, 1502-1509.
7. A. Ueno, K. Hori, & S. Nakasuda, Simultaneous learning of situation classification based on rewards and behavior selection based on the situation, Proc. 1996 IEEE/RSJ Int. Conf. on Intelligence Robots and Systems (IROS'96), 3, Osaka, Japan, 1996, 1510-1517.
8. T. Sawada, S. Ichikawa, & F. Hara. Autonomous action-mode change in a two-mobile robotics system: S-temperature based on-line learning, Proc. 1999 IEEE/RSJ Int. Conf. on Intelligence Robots and Systems (IROS'99), 1, Kyongju, Korea, 1999, 393-399.
9. B.J.A. Krose & J.W.M. van Dam, Adaptive state-space quantization for reinforcement learning of collision-free navigation, Proc. 1992 IEEE/RSJ Int. Conf. on Intelligence Robots and Systems (IROS'92), 2, Raleigh, NC, 1992, 1327-1332.
10. C. Claussen, S. Gutta, & H. Wechsler, Reinforcement learning using functional approximation for generalization and their application to cart centering and fractal compression, Proc. 16th Int. Joint Conf. on Artificial Intelligence, 2, Stockholm, Sweden, 1999, 1362-1367
11. T. Kohonen, Learning vector quantization for pattern recognition, Report TKK-F-A601, Helsinki University of Technology, Espoo, Finland, 1986.
12. C.J.C.H. Watkins, Learning from delayed rewards, doctoral diss., King's College, Cambridge, UK, 1989.
13. C. Touzet, Neural reinforcement learning for behaviour synthesis, Robotics and Autonomous Systems. 22(3-4), 1997, 251-282.
14. T. Kohonen, Self-organization and associative memory, 3rd ed., (Berlin, Heidelberg: Springer, 1989).
15. F. Fernández and D. Borrajo, VQQL: Applying vector quantization to reinforcement learning, RoboCup-99: Robot Soccer World Cup III (Stockholm, Sweden: Springer Verlag, 2000).
16. S.P. Lloyd, Least squares quantization in pcm, IEEE Trans. on Information Theory, 28, 1982, 127-135.
17. Y. Linde, A. Buzo, & R.M. Gray, An algorithm for vector quantizer design, IEEE Trans. on Communications, 1 (1), Com-28, 1980, 84-95.
18. L.E. Parker, A ease study for life-long learning and adaptation in cooperative robot teams, Proc. SPIE Sensor Fusion and Decentralized Control in Robotic Systems II, 3839, Boston, MA, 1999, 92-101.
19. B.B. Werger & M. Matarić, Broadcast of local eligibility for multi-target observation, in L.E. Parker, G. Bekey, & J. Barhem (Eds.), Distributed Autonomous Robotic Systems, 4, (Tokyo, Japan: Springer, 2000), 347-356.
20. J. Barhen & V. Protopopescu, Ultrafast neural network training for robot learning from uncertain data, Distributed Autonomous Robotic Systems, 4, Tokyo, 2000, 347-356.
21. L. Parker & C. Touzet, Multi-robot learning in a cooperative observation task, in L.E. Parker, G. Bekey, & J. Barhem (Eds.), Distributed Autonomous Robotic Systems, 4 (Tokyo, Japan: Springer, 2000) 391-401.
22. F. Fernández & D. Borrajo, Iterative VQQL for learning skills, Proc. of Learning '00, Leganés, Madrid, Spain, 2000.
23. C.J.C.H. Watkins & P. Dayan, Q-learning, Machine learning, 8, 1992, 279-292.
24. H. Kitano, M. Asada, Y. Kuniyoshi, I. Noda, & E. Osawa, Robocup: The robot world cup initiative, Proc. IJCAI-95 Workshop on Learning Robots, Montreal, Canada, 1995, 19-24.
25. I. Noda, Soccer server: A simulator of robocup, Proc. 4th Int. Symposium'95, Tokyo, Japan, 1995, 29-34.
26. D. Aha, ed., Lazy learning (Dordrecht: Kluwer, 1997).
27. J.C. Bezdek, T.R. Rechherzer, G.S. Lim, & Y. Attikiouzel, Multiple-prototype classifier design, IEEE Trans. on Systems, Man and Cybernetics, 28(1), 1998, 67-79.
28. B. Fritzke, Growing cell structures: A self-organizing network for unsupervised and supervised learning, Neural Networks, 7(9), 1994, 1441-1460.