Action-based sensor space segmentation for soccer robot learning

Applied Artificial Intelligence

Volumn 12, Issue 2-3, 1998, Pages 149-164

  Asada, Minoru ^a   Ichinoda, Sho ^a   Hosoda, Koh ^a  

^a OSAKA UNIVERSITY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; COMPUTER VISION; MOBILE ROBOTS; SENSORS; STATE SPACE METHODS; VECTORS;

ACTION-BASED SENSOR SPACE SEGMENTATION; REINFORCEMENT LEARNING;

ROBOT LEARNING;

EID: 0032019726     PISSN: 08839514     EISSN: 10876545     Source Type: Journal    
DOI: 10.1080/088395198117802     Document Type: Article

References (15)

1. Asada, M., S. Noda, S. Tawaratsumida, and K. Hosoda. 1995. Vision-based reinforcement learning for purposive behavior acquisition. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 146-153.
2. Chapman, D., and L. P. Kaelbling. 1991. Input generalization in delayed reinforcement learning: An algorithm and performance comparisons. In Proceedings ofIJCAI-91, pp. 726-731.
3. Connel J. H., and S. Mahadevan (eds.). 1993. Robot learning. Norwell, Mass.: Kluwer Academic.
4. Cramgr, H. 1951. Mathematical methods of statistics. Princeton, N. J.: Princeton University Press.
5. Dubrawski, A., and P. Reingnier. 1994. Learning to categorize perceptual space of a mobile robot using fuzzy-art neural network. In Proceedings ofIEEE/RSJIGI International Conference on Intelligent Robots and Systems 1994 (IROS’94), pp. 1272-1277.
6. Inoue, H. 1996. Research program on mechanisms for emergent machine intelligence. In Robotics research: The seventh international symposium, eds. G. Giralt and G. Hirzinger, pp. 162-170. New York: Springer.
7. Ishiguro, H., R. Sato, and T. Ishida. 1996. Robot oriented state space construction. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems 1996 (IROS96), pp. 1496-1501.
8. Kitano, H., M. Asada, Y. Kuniyoshi, I. Noda, and E. Osawa. 1995. Robocup: The robot world cup initiative. Presented at IJCAI-95 Workshop on Entertainment and AI/Alife.
9. Kröse, B. J. A., and J. W. M. Dam. 1992. Adaptive state space quantisation for reinforcement learning of collision-free navigation. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems 1992 (IROS ’92), pp. 1327-1332.
10. Mataric, M. 1994. Reward functions for accelerated learning. In Proceedings of Conference on Machine Learning-1994, pp. 181-189.
11. Nakamura, T., and M. Asada. 1995. Motion sketch: Acquisition of visual motion guided behaviors. In Proceedings of IJCAI-95, pp. 126-132.
12. Nakamura, T., and M. Asada. 1996. Stereo sketch: Stereo vision-based target reaching behavior acquisition with occlusion detection and avoidance. In Proceedings of IEEE International Conference on Robotics and Automation, pp. 1314-1319.
13. Sutton, R. S. 1992. Special issue on reinforcement learning. In R. S. Sutton (Guest ed.), Machine Learning 8.
14. Whitehead, S.D. 1991. A complexity analysis of cooperative mechanisms in reinforcement learning. In Proceedings AAAI-91, pp. 607-613.
15. Watkins, C. J. C. H., and P. Dayan. 1992. Technical note: Q-leaming. Machine Learning, 8:279-292.