Reinforcement learning of a continuous motor sequence with hidden states

Advanced Robotics

Volumn 21, Issue 10, 2007, Pages 1215-1229

  Arie, Hiroaki ^a   Ogata, Tetsuya ^b   Tani, Jun ^c   Sugano, Shigeki ^a  

^a WASEDA UNIVERSITY   (Japan)

^b KYOTO UNIVERSITY   (Japan)

^c RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

Author keywords

Actor critic method; Pendulum swing up; Perceptual aliasing problem; Recurrent neural network; Reinforcement learning

Indexed keywords

ALGORITHMS; BEHAVIORAL RESEARCH; NEUROLOGY; PARAMETER ESTIMATION;

ACTOR-CRITIC METHOD; PENDULUM SWING-UP; PERCEPTUAL ALIASING PROBLEM; RECURRENT NEURAL NETWORK;

REINFORCEMENT LEARNING;

EID: 34547543601     PISSN: 01691864     EISSN: 15685535     Source Type: Journal    
DOI: 10.1163/156855307781389365     Document Type: Article

References (18)

1. X. Huang and J. Weng, Novelty and reinforcement learning in the value system of developmental robots, in: Proc. 2nd Int. Workshop on Epigenetic Robotics(2002).
2. M. Asada, E. Uchibe and K. Hosoda, Cooperative behavior acquisition for mobile robots in dynamically changing real worlds via vision-based reinforcement learning and development, Artif. Intell.110, 275-292 (1999).
3. L.-J. Lin, Self-improving reactive agents based on reinforcement learning, Machine Learn.8, 293-321 (1992).
4. A. G. Barto, R. S. Sutton and C. W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems, IEEE Trans. Syst. Man Cybernet.13, 834-846 (1983).
5. R. Bianco and S. Nolfi, Evolving the neural controller for a robotic arm able to grasp objects on the basis of tactile sensors, Adapt. Behav.12, 37-45 (2004).
6. V. Gullapalli, A stochastic reinforcement learning algorithm for learning real-valued functions, Neural Networks3, 671-692 (1990).
7. K. Doya, Reinforcement learning in continuous time and space. Neural Comput.12, 219-245 (2000).
8. L.-J. Lin and T. M. Mitchell, Reinforcement learning with hidden state, in: Proc. 2nd Int. Conf. on Simulation of Adaptive Behavior(1993).
9. J. Tani, Model-based learning for mobile robot navigation from the dynamical system perspective, IEEE Trans. Syst. Man Cybernet. B26, 421-436 (1996).
10. A. Kachites McCallum, Reinforcement learning with selective perception and hidden state, PhD Thesis, Univertsity of Rochester (1995).
11. R. S. Sutton, Learning to predict by the methods of temporal difference, Machine Learn.3, 9-44 (1988).
12. K. Doya, Temporal Difference Learning in Continuous Time and Space, volume 8 of Advances in Neural Information Processing Systems. MIT Press, Cambridge, MA (1996).
13. R. J. Williams and D. Zipser, A learning algorithm, for continually running fully recurrent neural networks, Neural Comput.1, 270-280 (1989).
14. M. I. Jordan and D. E. Rumelhart, Forward models: supervised learning with a distal teacher, Cognitive Sci.16, 307-354 (1992).
15. D. Rumelhart, G. Hinton and R. Williams, Learning Internal Representations by Error Propagation, volume 1 of Parallel Distributed Processing. MIT Press, Cambridge, MA (1986).
16. J. Tani, An interpretation of the "self" from the dynamical system perspective: a constructivist approach, Consciousness Studies5 (1998).
17. C. W. Anderson, Strategy learning with multilayer connectionist representations, in: Proc. 4th Int. Workshop on Machine Learning, pp. 103-114 (1987).
18. Y Bengio, P. Simard and P. Frasconi, Learning long-term dependencies with gradient descent is difficult, IEEE Trans. Neural Networks5, 157-166 (1994).