Reinforcement learning with a supervisor for a mobile robot in a real-world environment

Proceedings of the 2007 IEEE International Symposium on Computational Intelligence in Robotics and Automation, CIRA 2007

Volumn , Issue , 2007, Pages 73-78

  Conn, Karla ^a   Peters, Richard Alan ^a  

^a VANDERBILT UNIVERSITY   (United States)

Author keywords

Mobile robots; Q learning; Reinforcement learning

Indexed keywords

MOBILE ROBOTS; REMOTE CONTROL; ROBUSTNESS (CONTROL SYSTEMS); SUPERVISORY PERSONNEL;

EXPERIMENTAL ANALYSIS; Q-LEARNING; RL ALGORITHMS;

REINFORCEMENT LEARNING;

EID: 34948845102     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CIRA.2007.382878     Document Type: Conference Paper

References (16)

1. G. Tesauro, "Temporal-difference learning and TD-Gammon," Communications of the ACM, 38(3), 1995.
2. th Int. Conf. on Machine Learning, 2000.
3. th Int. Conf. on Algorithmic Learning Theory, 2002.
4. T. S. Dahl, M. J. Matarió, and G. S. Sukhatme, "Adaptive spatiotemporal organization in groups of robots," in Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, 2002.
5. I. Ghory, "Reinforcement learning in board games," Tech. Report CSTR-04-004, CS Dept., Univ. of Bristol, May 2004.
6. J. Provost, B. J. Kuipers, and R. Miikulainen, "Self-Organizing perceptual and temporal abstraction for robot reinforcement learning," in AAAI-04 Workshop on Learning and Planning in Markov Processes, pp. 79-84, 2004.
7. th European Workshop on Learning Robots (EWLR-61997), 1997.
8. W. D. Smart and L. P. Kaelbling, "Effective reinforcement learning for mobile robots," in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA), vol. 4, pp. 3404-3410, 2002.
9. T. Martínez-Marín and T. Duckett, "Fast reinforcement learning for vision-guided mobile robots," in Proc. IEEE Int. Conf. on Robotics and Automation (ICRA), pp. 1425-1430, 2005.
10. R. Sutton and A. Barto, Reinforcement Learning: An Introduction. MIT Press, 1998.
11. W. Schultz, P. Dayan, and R. Montague, "A neural substrate of prediction and reward," Science, vol. 275, pp.1593-1599, 1997.
12. C. J. C. H. Watkins and P. Dayan, "Q-learning," Machine Learning, vol. 8, pp.279-292, 1992.
13. B. Gerkey, R. Vaughan, and A. Howard, "The Player/Stage project: tools for multi-robot and distributed sensor systems," in Proc. Int. Conf. on Advanced Robotics, pp. 317-323, 2003.
14. "Can Ethernet be real-time?," Network Data Delivery Service (NDDS), http://www.rti.com/products/ndds/literature.html.
15. M. Huber and R. A. Grupen, "A hybrid architecture for learning robot control tasks," Robotics Today, vol. 13, RI/SME, 2000.
16. P. Cook, and G. Hayes, "Could active perception aid navigation of partially observable grid worlds?," Lecture Notes in Computer Science, vol. 2837, pp.72-83, March 2003.