Neural reinforcement learning for behaviour synthesis

Robotics and Autonomous Systems

Volumn 22, Issue 3-4, 1997, Pages 251-281

  Touzet, Claude F ^a,b  

^a AIX MARSEILLE UNIVERSITY   (France)

^b OAK RIDGE NATIONAL LABORATORY   (United States)

Author keywords

Autonomous robotics; Neural Q learning; Obstacle avoidance behaviour; Reinforcement learning; Self organising map

Indexed keywords

COLLISION AVOIDANCE; LEARNING SYSTEMS; NEURAL NETWORKS; ROBOTICS;

AUTONOMOUS ROBOTICS; NEURAL Q LEARNING; REINFORCEMENT LEARNING;

MOBILE ROBOTS;

EID: 0031341345     PISSN: 09218890     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0921-8890(97)00042-0     Document Type: Article

References (27)

1. D. Ackley and M. Littman, Interactions between learning and evolution, in: C.G. Langton et al., eds., Artificial Life II, SFI Studies Sc. Complexity, Vol X (Addison-Wesley, Reading, MA, 1991) 487-509.
2. J.S. Albus, A new approach to manipulator control: The cerebellar model articulation controller (CMAC), Transactions of the ASME (1975).
3. A.G. Barto and P. Anandan, Pattern recognizing stochastic leaning automata, IEEE Transactions on Systems, Man and Cybernetics SMC-15 (1985) 360-375.
4. A.G. Barto, R.S. Sutton and C.W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems, IEEE Transactions on Systems, Man and Cybernetics SMC-13 (1983) 834-846.
5. V. Braitenberg, Vehicles: Experiments in Synthetic Psychology (MIT Press, Cambridge, MA, 1986).
6. G.A. Carpenter and S. Grossberg, The ART of adaptive pattern recognition by a self-roganizing neural network, Proceedings of the IEEE (1988).
7. M. Colombetti, M. Dorigo and G. Borghi, Behavior analysis and training - A methodology for behavior engineering, in: M. Dorigo, ed., Special Issue on Learning Autonomous Robots, IEEE Transactions on Systems, Man and Cybernetics SMC-part B 26 (3) (1996) 365-380.
8. J. del R. Millàn, Rapid, safe and incremental learning of navigation strategies, in: M. Dorigo, ed., Special Issue on Learning Autonomous Robots, IEEE Transactions on Systems, Man and Cybernetics, SMC-part B 26 (3) (1996) 408-420.
9. M. Dorigo and M. Colombetti, Robot shaping: Developing autonomous agents through learning, Artificial Intelligence 71 (2) (1994) 321-370.
10. O. Holland and M. Snaith, Extending the adaptive heuristic critic and Q-learning: From facts to implications, in: I. Alexander and J. Taylor, eds., Artificial Neural Networks, Vol. 2 (Elsevier, Amsterdam, 1992) 599-602.
11. L. Kaelbling, Learning in Embedded Systems (MIT Press, Cambridge, MA, 1993).
12. L. Kaelbling, M. Littman and A. Moore, Reinforcement learning: A survey, Journal of Artificial Intelligence Research 4 (1996) 237-285.
13. T. Kohonen, Self-Organisation and Associative Memory (Springer, Berlin, 1984).
14. L.J. Lin, Self-improving reative agents based on reinforcement learning, planning and teaching, Machine Learning 8 (1992) 293-321.
15. L.-J. Lin, Reinforcement learning for robots using neural networks, Ph.D. Thesis, in: C.G. Langton et al., eds., Carnegie Mellon University, Pittsburgh, CMU-CS-93-103, 1993.
16. S. Mahadevan and J. Connell, Automatic programming of behavior-based robots using reinforcement learning, Artificial Intelligence 55 (2) (1991) 311-365.
17. M. Mataric, Reward function for accelerated learning, in: W.W. Cohen and H. Hirsh, eds., Proc. of 11th Int. Conf. on Machine Learning (Morgan Kaufman, LOS Altos, CA, 1994).
18. R.A. McCallum, Using transitional proximity for faster reinforcement learning, Proc. 9th Int. Conf. on Machine Learning (Morgan Kaufman, LOS Altos, CA, 1992).
19. F. Mondada, E. Franzi and P. Ienne, Mobile robot miniaturisation: A tool for investigation in control algorithms, Proc. 3rd Int. Symp. on Experimental Robotics, Kyoto, Japan (1993).
20. D. Rumelhart, G. Hinton and R. Williams, Learning internal representations by error propagation, in: D. Rumelhart and J. Mc Clelland, eds., Parallel Distributed Processing, Vol. 1 (MIT Press, Cambridge, MA, 1986) 318-362.
21. S. Sehad and C. Touzet, Reinforcement learning and neural reinforcement learning, in: M. Verleysen, ed., ESANN 94 (D-Facto Publication, Brussels, 1994).
22. R.S. Sutton, Reinforcement learning architectures for a animats, in: J.-A. Meyer and S.W. Wilson, eds., Proc. 1st Int. Conf. on Simulation of Adaptive Behavior, From Animals to Animats (MIT Press, Cambridge, MA, 1991) 288-296.
23. C. Touzet and N. Giambiasi, The connectionist sequential machine: A general model of sequential networks, in: Canberra P. Leong and M. Jabri, eds., Australian Conf. on Neural Networks (Sydney University Electrical Engineering NSW 2006 (1992).
24. C. Touzet and N. Giambiasi, Application of connectionist models to fuzzy inference systems, in: B. Fronhöfer and G. Wrightson, eds., Parallelization in Inference Systems, Lectures Notes in Artifical Intelligence, Vol. 590 (Springer, Berlin, 1992).
25. C. Touzet, S. Sehad and N. Giambiasi, Improving reinforcement learning of obstacle avoidance behavior with forbidden sequences of actions, Int. Conf. on Robotics and Manufacturing, Cancun, Mexico (1995).
26. W.G. Walter, An imitation of life, Scientific American 182 (5) (1950) 42-45.
27. C.J.C.H. Watkins, Learning from delayed rewards, Ph.D. Thesis, King's College, Cambridge, UK, 1989.