Anticipating rewards in continuous time and space with echo state networks and actor-critic design

ESANN 2011 - 19th European Symposium on Artificial Neural Networks

Volumn , Issue , 2011, Pages 117-122

  Oubbati, Mohamed ^a   Kächele, Markus ^a   Koprinkova Hristova, Petia ^b   Palm, Günther ^a  

^a UNIVERSITY OF ULM   (Germany)

^b BULGARIAN ACADEMY OF SCIENCES   (Bulgaria)

Author keywords

[No Author keywords available]

Indexed keywords

CONTINUOUS TIME SYSTEMS; MACHINE DESIGN; ROBOTS;

ACTOR CRITIC; CONTINUOUS-TIME; ECHO STATE NETWORKS; OPTIMAL CONTROL POLICY;

NEURAL NETWORKS;

EID: 85088916195     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Stuart E. Dreyfus and Averill M. Law. Art and Theory of Dynamic Programming. Academic Press, Inc., Orlando, FL, USA, 1977.
2. A. G. Barto, Richard S. Sutton, and Charles W. Anderson. Neuronlike adaptive elements that can solve difficult learning control problems. pages 81–93, 1990.
3. D. Prokhorov and D. Wunsch. Adaptive critic designs. IEEE Transactions on Neural Networks, 8:997–1007, 1997.
4. K. Funahashi and Y. Nakamura. Approximation of dynamical systems by continuous time recurrent neural networks. Neural Network, 6(6):801–806, 1993.
5. Jaeger H. The’echo state’ approach to analysing and training recurrent neural networks. Technical Report 148, AIS Fraunhofer, St. Augustin, Germany, 2001.
6. H. P. Koprinkova, M. Oubbati, and G. Palm. Adaptive critic design with echo state network. In IEEE International Conference on Systems, Man, and Cybernetics, pages 1010–1015, 2010.
7. H. Jaeger. Tutorial on training RNNs, covering BPPT, RTRL, EKF and the echo state network approach. Technical Report 159, AIS Fraunhofer, Germany, 2002.