D. E. Moriarty and R. Miikkulainen, "E#cient Reinforcement Learning Through Symbiotic Evolution," Machine Learning, vol. 22, pp. 11-32, 1997. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Evolving Rules for Nonlinear Control - Bobbin, Yao (1999) (Correct)
....by the genes it is using. There will also exist biases in the representation which a ect the trajectory that the evolution will take to arrive at the solution. There has been a variety of representations used to evolve controllers, including binary strings [3, 4] weights in a neural network [5, 6, 7], mathematical functions in a genetic program [2, Page 289] 8] and parameters for a model of the system being controlled [7] A strength of the evolutionary process is the fact that it can operate on a diverse range of structures. A representation can be chosen which is appropriate for the ....
D. E. Moriarty and R. Miikkulainen, \Ecient reinforcement learning through symbiotic evolution," Machine Learning, vol. 22, pp. 11-33, 1996.
Intensive Reinforcement Learning - Wawrzyski (2005) (Correct)
No context found.
D. E. Moriarty and R. Miikkulainen, "E#cient Reinforcement Learning Through Symbiotic Evolution," Machine Learning, vol. 22, pp. 11-32, 1997.
International Journal of Neural Systems, Vol. 9, No. 6.. - World Scientific.. (Correct)
No context found.
D. E. Moriarty and R. Miikkulainen 1996, "E#cient reinforcement learning through symbiotic evolution," Machine Learning 22, 11--32.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC