Using Adaptive Dynamic Programming to Understand and Replicate Brain Intelligence: the Next Level Design

Since the 1960s I proposed that we could understand and replicate the highest level of intelligence seen in the brain, by building ever more capable and general systems for adaptive dynamic programming (ADP), which is like reinforcement learning but based on approximating the Bellman equation and allowing the controller to know its utility function. Growing empirical evidence on the brain supports this approach. Adaptive critic systems now meet tough engineering challenges and provide a kind of first-generation model of the brain. Lewis, Prokhorov and myself have early second-generation work. Mammal brains possess three core capabilities, creativity/imagination and ways to manage spatial and temporal complexity, even beyond the second generation. This paper reviews previous progress, and describes new tools and approaches to overcome the spatial complexity gap.

[1]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[2]  Paul J. Werbos,et al.  Applications of advances in nonlinear sensitivity analysis , 1982 .

[3]  Warren B. Powell,et al.  Handbook of Learning and Approximate Dynamic Programming , 2006, IEEE Transactions on Automatic Control.

[4]  P. Werbos.  Backwards Differentiation in AD and Neural Nets: Past Links and New Opportunities , 2006 .

[5]  Robert Kozma,et al.  Cellular SRN Trained by Extended Kalman Filter Shows Promise for ADP , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[6]  Paul J. Werbos,et al.  Stable adaptive control using new critic designs , 1998, Other Conferences.

[7]  Paul J. Werbos,et al.  The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting , 1994 .

[8]  E. Feigenbaum,et al.  Computers and Thought , 1963 .

[9]  Wesley R. Elsberry,et al.  Optimality in Biological and Artificial Networks , 1997 .

[10]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[11]  E. Rowland.  Theory of Games and Economic Behavior , 1946, Nature.

[12]  Eduardo D. Sontag,et al.  Neural Networks for Control , 1993 .

[13]  Paul J. Werbos,et al.  What do neural nets and quantum theory tell us about mind and reality , 2002, q-bio/0311006.

[14]  R. Godson.  Elements of intelligence , 1979 .

[15]  Kevin Warwick,et al.  A Brain-Like Design to Learn Optimal Decision Strategies in Complex Environments , 1998 .