Hierarchical Representations of Behavior for Efficient Creative Search

Options Results Experiments Creative Search We adopt a Darwinian view of creativity, in which creative products are • assembled through a sequential decision process in a trial-and-error fashion. This search process consists of trajectories through the space of creative • products and selective retention of highly-valued results (and the means for constructing them). An explict population is not maintained, however. Rather, an implict “pop• ulation” of potential creative products exists at a given time, any member of which can be realized via some behavioral operator. One “member” of each “population” is thus selected at each step given the • current product (context), and a new “population” results at the next step.

[1]  D. Campbell Blind variation and selective retention in creative thought as in other knowledge processes. , 1960, Psychological review.

[2]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[3]  C. Watkins Learning from delayed rewards , 1989 .

[4]  Keiji Kanazawa,et al.  A model for reasoning about persistence and causation , 1989 .

[5]  Richard S. Sutton,et al.  Integrated Modeling and Control Based on Reinforcement Learning and Dynamic Programming , 1990, NIPS 1990.

[6]  John R. Koza,et al.  Genetic programming - on the programming of computers by means of natural selection , 1993, Complex adaptive systems.

[7]  Craig Boutilier,et al.  Exploiting Structure in Policy Construction , 1995, IJCAI.

[8]  Doina Precup,et al.  Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning , 1999, Artif. Intell..

[9]  D. Simonton Origins of genius : Darwinian perspectives on creativity , 1999 .

[10]  Craig Boutilier,et al.  Stochastic dynamic programming with factored representations , 2000, Artif. Intell..

[11]  L. Gabora Creative Thought as a nonDarwinian Evolutionary Process , 2004, nlin/0411057.

[12]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[13]  L. Gabora Creative Thought as a non Darwinian Evolutionary Process , 2005 .

[14]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[15]  Olivier Sigaud,et al.  Learning the structure of Factored Markov Decision Processes in reinforcement learning problems , 2006, ICML.

[16]  Andrew G. Barto,et al.  Causal Graph Based Decomposition of Factored MDPs , 2006, J. Mach. Learn. Res..