Efficient learning of reactive robot behaviors with a neural-Q_learning approach

IEEE International Conference on Intelligent Robots and Systems

Volumn 1, Issue , 2002, Pages 1020-1025

  Carreras, Marc ^a   Ridao, Pere ^a   Batlle, Joan ^a   Nicosevici, Tudor ^a  

^a UNIVERSITY OF GIRONA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING ALGORITHMS; MULTILAYER NEURAL NETWORKS; ONLINE SYSTEMS; SYSTEM STABILITY;

ONLINE LEARNING; REACTIVE ROBOTS; REINFORCEMENT LEARNING;

ROBOT LEARNING;

EID: 0036450627     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (12)

1. R. Arkin, Behavior-based Robotics. MIT Press, 1998.
2. J.A. Bagnell and J.G. Schneider, 'Autonomous Helicopter Control using Reinforcement Learning Policy Search Methods', IEEE International Conference on Robotics & Automation, Korea, 2001.
3. K. Baird, 'Residual Algorithms: Reinforcement Learning with Function Approximation', Machine Learning: Twelfth International Conference, San Francisco, USA, 1995.
4. M. Carreras, J. Batlle and P. Ridao, 'Hybrid Coordination of Reinforcement Learning-based Behaviors for AUV control', IEEE/RSJ IROS, Hawaii, USA 2001.
5. C. Gaskett, D. Wettergreen and A. Zelinsky, 'Q-learning in continuous state and action spaces', Proc. of the 12th Australian Joint Conference on Artificial Intelligence, Sydney, Australia, 1999.
6. S. Haykin, Neural Networks, a comprehensive foundation. Prentice Hall, 2nd ed., 1999.
7. N. Hernandez and S. Mahadevan, 'Hierarchical Memory-Based Reinforcement Learning', Fifteenth International Conference on Neural Information Processing Systems, Denver, USA, 2000.
8. W.D. Smart and L.P. Kaelbling, 'Practical Reinforcement Learning in Continuous Spaces', Intern. Conference on Machine Learning, 2000.
9. R. Sutton, and A. Barto, Reinforcement Learning, an introduction. MIT Press, 1998.
10. Y. Takahashi, M. Takada, and M. Asada, 'Continuous Valued Q-learning for Vision-Guided Behavior Acquisition'. Intern. Conference on Multisensor Fusion and Integration for Intelligent Systems, 1999.
11. M. Takeda, T. Nakamura and T. Ogasawara, 'Continuous Valued Q-learning Method Able to Incrementally Refine State Space', IEEE/RSJ IROS, Hawaii, USA 2001.
12. C.J.C.H. Watkins and P. Dayan, 'Q-learning', Machine Learning, 8:279-292, 1992.