A two-step algorithm for learning from unspecific reinforcement

Journal of Physics A: Mathematical and General

Volumn 32, Issue 31, 1999, Pages 5749-5762

  Kühn, Reimer ^a   Stamatescu, Ion Olimpiu ^a,b  

^a INSTITUT FÜR THEORETISCHE PHYSIK   (Germany)

^b FEST   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0040122271     PISSN: 03054470     EISSN: None     Source Type: Journal    
DOI: 10.1088/0305-4470/32/31/301     Document Type: Article

References (14)

1. Hertz J, Krogh A and Palmer RG 1991 Introduction to the Theory of Neural Computation (Reading, MA: Addison-Wesley)
2. Kaelbling L P (ed) 1996 Machine Learning 22
3. Watkins C J C H 1989 Learning from delayed rewards PhD Thesis unpublished
4. Sutton R S 1988 Machine Learning 3 9
5. Barto A G, Sutton R S and Anderson Ch W 1983 IEEE Trans. Syst. Man Cybernetics 13 834
6. Mlodinow L and Stamatescu I-O 1985 Int. J. Comput. Inform. Sci. 14 201
7. Stamatescu I-O 1998 Statistical features in learning (contribution to LEARNING '98, Madrid) Preprint condmat/9809135
8. Stamatescu I-O 1996 The neural network approach Proc. 1st Int. Conf. Philosophy of Science: Philosophy of Biology (Vigo, 1996) ed J T Suarez (Vigo: University of Vigo) p 311
9. Biehl M, Kühn R and Stamatescu I-O in preparation
10. Biehl M and Riegler P 1994 Europhys. Lett. 28 525
11. Vallet F 1989 Europhys. Lett. 8 747
12. Kinouchi O and Caticha N 1992 J. Phys. A: Math. Gen. 25 6243
13. Biehl M and Schwarze H 1992 Europhys. Lett. 20 733
14. Bös S 1998 J. Phys. A: Math. Gen. 31 L413