Three Architectures for Continuous Action
作者： Stewart W. Wilson
DOI: 10.1007/978-3-540-71231-2_16
关键词:
摘要: Three classifier system architectures are introduced that permit the systems to have continuous (non-discrete) actions. One is based on interpolation, second an actor-critic paradigm, and third treating action as a variable homogeneous with input. While last architecture appears most interesting promising, all three offer potential directions toward action, goal hardly addressed.
springer.com
sci-hub.st 参考文章(14)
Stewart W. Wilson, Function approximation with a classifier system genetic and evolutionary computation conference. pp. 974- 981 ,(2001)
Stewart W. Wilson, Classifier Systems for Continuous Payoff Environments Genetic and Evolutionary Computation – GECCO 2004. pp. 824- 835 ,(2004) , 10.1007/978-3-540-24855-2_96
Damien Ernst, Arthur Louette, Introduction to Reinforcement Learning MIT Press. ,(1998)
Stewart W. Wilson, Classifier fitness based on accuracy Evolutionary Computation. ,vol. 3, pp. 149- 175 ,(1995) , 10.1162/EVCO.1995.3.2.149
Pier Luca Lanzi, Daniele Loiacono, Stewart W. Wilson, David E. Goldberg, Generalization in the XCSF Classifier System: Analysis, Improvement, and Extension Evolutionary Computation. ,vol. 15, pp. 133- 168 ,(2007) , 10.1162/EVCO.2007.15.2.133
Pier Luca Lanzi, Stewart W. Wilson, Toward Optimal Classifier System Performance in Non-Markov Environments Evolutionary Computation. ,vol. 8, pp. 393- 418 ,(2000) , 10.1162/106365600568239
Pier Luca Lanzi, Daniele Loiacono, Stewart W. Wilson, David E. Goldberg, Extending XCSF beyond linear approximation Proceedings of the 2005 conference on Genetic and evolutionary computation - GECCO '05. pp. 1827- 1834 ,(2005) , 10.1145/1068009.1068319
M. V. Butz, S. W. Wilson, An algorithmic description of XCS soft computing. ,vol. 6, pp. 144- 153 ,(2002) , 10.1007/S005000100111
A.G. Barto, R.S. Sutton, Reinforcement Learning: An Introduction ,(1988)
M.V. Butz, T. Kovacs, P.L. Lanzi, S.W. Wilson, Toward a theory of generalization and learning in XCS IEEE Transactions on Evolutionary Computation. ,vol. 8, pp. 28- 46 ,(2004) , 10.1109/TEVC.2003.818194