Geodesic
Simulation of evolution of autonomous adaptive agents
Matematičeskoe modelirovanie, Tome 20 (2008) no. 2, pp. 21-31.

Voir la notice de l'article provenant de la source Math-Net.Ru

A model of evolving populations of self-learning agents is studied and the interaction between learning and evolution is analyzed. Each agent is equipped with a neural network adaptive critic design for behavioral adaptation. The model is investigated for the case of a simple agent-broker that predicts stock price changes and uses its predictions for selecting actions. Three cases are analyzed in which either evolution or learning, or both, are active in this model. It is shown that the Baldwin effect can be observed in this model, viz., originally acquired adaptive policy of agents becomes inherited over the course of the evolution. Also the behavioral tactics of our agents is compared to the searching behavior of simple animals. 
@article{MM_2008_20_2_a2,
     author = {O. P. Mosalov and V. G. Red'ko and D. V. Prokhorov},
     title = {Simulation of evolution of autonomous adaptive agents},
     journal = {Matemati\v{c}eskoe modelirovanie},
     pages = {21--31},
     publisher = {mathdoc},
     volume = {20},
     number = {2},
     year = {2008},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MM_2008_20_2_a2/}
}
TY  - JOUR
AU  - O. P. Mosalov
AU  - V. G. Red'ko
AU  - D. V. Prokhorov
TI  - Simulation of evolution of autonomous adaptive agents
JO  - Matematičeskoe modelirovanie
PY  - 2008
SP  - 21
EP  - 31
VL  - 20
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MM_2008_20_2_a2/
LA  - ru
ID  - MM_2008_20_2_a2
ER  - 
%0 Journal Article
%A O. P. Mosalov
%A V. G. Red'ko
%A D. V. Prokhorov
%T Simulation of evolution of autonomous adaptive agents
%J Matematičeskoe modelirovanie
%D 2008
%P 21-31
%V 20
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MM_2008_20_2_a2/
%G ru
%F MM_2008_20_2_a2
O. P. Mosalov; V. G. Red'ko; D. V. Prokhorov. Simulation of evolution of autonomous adaptive agents. Matematičeskoe modelirovanie, Tome 20 (2008) no. 2, pp. 21-31. http://geodesic.mathdoc.fr/item/MM_2008_20_2_a2/

[1] Tarasov V. B., Ot mnogoagentnykh sistem k intellektualnym organizatsiyam: filosofiya, psikhologiya, Editorial URSS, M., 2002, 352 pp.

[2] Sutton R., Barto A., Reinforcement Learning: An Introduction, MIT Press, Cambridge, 1998; See also: http://www.cs.ualberta.ca/~sutton/book/the-book.html

[3] Prokhorov D., Puskorius G., Feldkamp L., “Dynamical neural networks for control”, A field guide to dynamical recurrent networks, eds. J. Kolen and S. Kremer, IEEE Press, NY, 2001, 257–289

[4] Moody J., Wu L., Liao Y., Saffel M., “Performance function and reinforcement learning for trading systems and portfolios”, Journal of Forecasting, 17 (1998), 441–470 | 3.0.CO;2-%23 class='badge bg-secondary rounded-pill ref-badge extid-badge'>DOI

[5] Redko V. G., Prokhorov D. V., “Neirosetevye adaptivnye kritiki”, Nauchnaya sessiya MIFI-2004. VI Vserossiiskaya nauchno-tekhnicheskaya konferentsiya “Neiroinformatika-2004”, Sbornik nauchnykh trudov. Chast 2, MIFI, M., 2004, 77–84

[6] Prokhorov D. V., Wunsch D. C., “Adaptive critic designs”, IEEE Transactions on Neural Networks, 8 (1997), 997–1007 | DOI

[7] Rumelhart D. E., Hinton G. E., Williams R. G., “Learning representation by back-propagating error”, Nature, 323 (1986), 533–536 | DOI

[8] Baldwin J. M., “A new factor in evolution”, American Naturalist, 30 (1896), 441–451 | DOI

[9] Turney P., Whtley D., Anderson R. (Eds.), “Evolution, Learning, and Instinct: 100 Years of the Baldwin Effect”, Special Issue of Evolutionary Computation on the Baldwin Effect, 4:3 (1996)

[10] Nepomnyashchikh V. A., “Selection behaviour in caddis fly larvae”, From Animals to Animats 5, Proceedings of the Fifth International Conference of the Society for Adaptive Behavior, eds. R. Pfeifer et al., MIT Press, Cambridge, MA, 1998, 155–160

[11] Nepomnyaschikh V. A., “Kak zhivotnye reshayut plokho formalizuemye zadachi poiska”, Sinergetika i psikhologiya, Teksty. Vypusk 3. Kognitivnye protsessy, eds. Arshinov V.I., Trofimova I. N., Shendyapin V. M., Izdatelstvo Kognito-tsentr, M., 2004, 197–209