Neural combinatorial learning of goal-directed behavior with reservoir critic and reward modulated hebbian plasticity

Proceedings - 2013 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2013

Volumn , Issue , 2013, Pages 993-1000

  Dasgupta, Sakyasingha ^a   Wörgötter, Florentin ^a   Morimoto, Jun ^b   Manoonpong, Poramate ^a  

^a UNIVERSITY OF GÖTTINGEN   (Germany)

^b ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

Author keywords

Correlation learning; Re inforcement learning; Reservoir networks; Temporal memory

Indexed keywords

CLASSICAL CONDITIONING; GOAL-DIRECTED BEHAVIOR; MOBILE ROBOT SYSTEMS; OPERANT CONDITIONING; PARTIALLY OBSERVABLE MARKOV DECISION PROCESS; RADIAL BASIS FUNCTION(RBF); RESERVOIR NETWORKS; TEMPORAL MEMORY;

CYBERNETICS; RADIAL BASIS FUNCTION NETWORKS;

LEARNING SYSTEMS;

EID: 84893615072     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/SMC.2013.174     Document Type: Conference Paper

References (16)

1. Doya, K. (2000) Reinforcement Learning In Continuous Time and Space. Neural Computation, 12, 219-245.
2. Dasgupta, S., Wörgötter, F., and Manoonpong, P. (2013) Information Dynamics based Self-adaptive Reservoir for Delay Temporal Memory Tasks. Evolving Systems, doi: 10.1007/s12530-013-9080-y.
3. Frémaux, N., Sprekeler, H., Gerstner, W. (2013), Reinforcement Learning Using a Continuous Time Actor-Critic Framework with Spiking Neurons. PLoS Comput Biol 9(4): e1003024. doi:10.1371/journal.pcbi.1003024.
4. Jaeger, H., and Haas, H. (2004): Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science, 304(5667), 78-80.
5. Maass, W., Natschlger, T., and Markram, H. (2002), Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation. 14 (11): 253160.
6. Legenstein, R., Chase, S.M., Schwartz, A.B., and Maass, W. (2010) A reward-modulated hebbian learning rule can explain experimentally observed network reorganization in a brain control task. J Neurosci 30:84008410.
7. Manoonpong, P., Wörgötter, F., and Morimoto, J. (2010) Extraction of Reward-Related Feature Space Using Correlation-Based and Reward- Based Learning Methods. In Proc. 17th International Conference on Neural Information Processing, Sydney, Australia, November 22-25 (ICONIP'10), Part I, LNCS 6443, pp. 414-421.
8. Manoonpong, P., Kolodziejski, C., Wörgötter, F., and Morimoto J. (2013) Combining Correlation-Based and Reward-Based Learning in Neural Control for Policy Improvement. Advances in Complex Systems, doi: 10.1142/S021952591350015X.
9. Morimoto, J., and Kenji, Doya. (1998) Reinforcement learning of dynamic motor sequence: Learning to stand up. In Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol. 3. IEEE.
10. Oubbati, M., Kchele, M., Koprinkova-Hristova, P., and Palm, G. (2011), Anticipating Rewards in Continuous Time and Space with Echo State Networks and Actor-Critic Design. In Proc. 19th European Symposium on Artificial Neural Networks (ESANN).
11. Koprinkova-Hristova, P., Oubbati, M., and Palm, G. (2010). Adaptive critic design with echo state network. In Proc. IEEE International Conference on Systems, Man, and Cybernetics, 1010-1015.
12. Pavlov, I., Conditioned reflexes (Oxford University Press, Oxford, UK, 1927).
13. Porr, B., and Wörgötter, F. (2006), Strongly improved stability and faster convergence of temporal sequence learning by utilising input correlations only. Neural computation 18, 1380-1412.
14. Skinner, B., The Behavior of Organisms: An Experimental Analysis (Appleton Century Croft, New York, 1938).
15. Triesch, J. (2007), Synergies between Intrinsic and Synaptic Plasticity Mechanisms. Neural Computation 4, 885-909.
16. Wörgötter, F., and Porr, B. (2004) Temporal sequence learning, prediction and control - A review of different models and their relation to biological mechanism. Neural Computation. 17, 245-319. 1000.