In this paper we study how individual learning interacts with an evolutionary algorithm in its search for good solutions to the Busy Beaver problem. Two learning strategies, the Baldwin Effect and Lamarckian learning, are compared with an extensive set of experiments. Results show that the Baldwin Effect is less sensitive to specific issues concerning the definition of the learning model and it is more effective in adjusting its learning power to maximise the search performance of the evolutionary algorithm. Some insight about the specific role that evolution and learning play during search is also presented.
Cited by
Year 2012 : 1 citations
S Whiteson. Evolutionary Computation for Reinforcement Learning. Reinforcement Learning, 2012 - Springer
Year 2010 : 1 citations
Shimon A. Whiteson. Adaptive Representations for Reinforcement Learning. Studies in Computational Intelligence, Springer, 2010.
Year 2009 : 1 citations
T Kovacs. Genetics-based machine learning. Handbook of Natural Computing: Theory, Experiments, 2009.
Year 2007 : 1 citations
Shimon A. Whiteson (2007). Adaptive Representations for Reinforcement Learning, Ph.D. Thesis, The University of Texas at Austin.
Year 2006 : 2 citations
S. Whiteson, P. Stone. Evolutionary Function Approximation for Reinforcement Learning. Journal of Machine Learning Research, Vol. 7, pp. 877-917
D. Curran (2006). An Empirical Analysis of Cultural Learning: Examining Fitness, Diversity and Changing Environments in Populations of Game-Playing Network Agents. Ph.D. Thesis, National University of Ireland, Galway, Ireland.
Year 2002 : 1 citations
COELHO, Leandro dos Santos; KROHLING, Renato A. "Discrete Variable Structure Control Design based on Lamarckian Evolution. In: 7TH ONLINE WORLD CONFERENCE ON SOFT COMPUTING IN INDUSTRIAL APPLICATIONS, 2002. Advances in Soft Computing: Engineering Design and Manufacturing. Springer-Verlag, 2002. v. 1, p. 361-370
