Bottom-up Skill Learning in Reactive Sequential Decision Tasks

This paper introduces a hybrid model that unifies connectionist, symbolic, and reinforcement learning into an integrated architecture for bottom-up skill learning in reactive sequential decision tasks. The model is designed for an agent to learn continuously from on-going experience in the world, without the use of preconceived concepts and knowledge. Both procedural skills and high-level knowledge are acquired through an agent’s experience interacting with the world. Computational experiments with the model in two domains are reported.

[1]  R. Shiffrin,et al.  Controlled and automatic human information processing: I , 1977 .

[2]  Tom M. Mitchell,et al.  Generalization as Search , 2002 .

[3]  John R. Anderson.  Acquisition of cognitive skill. , 1982 .

[4]  D. Broadbent,et al.  On the Relationship between Task Performance and Associated Verbalizable Knowledge , 1984 .

[5]  Nada Lavrac,et al.  The Multi-Purpose Incremental Learning System AQ15 and Its Testing Application to Three Medical Domains , 1986, AAAI.

[6]  P. Ackerman.  Determinants of individual differences during skill acquisition: Cognitive abilities and information processing. , 1988 .

[7]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[8]  Daniel B. Willingham,et al.  On the development of procedural knowledge. , 1989, Journal of experimental psychology. Learning, memory, and cognition.

[9]  R. Sun.  On Variable Binding in Connectionist Networks , 1992 .

[10]  J. Kruschke,et al.  ALCOVE: an exemplar-based connectionist model of category learning. , 1992, Psychological review.

[11]  A. Reber.  Implicit learning and tacit knowledge , 1993 .

[12]  John R. Anderson,et al.  Rules of the Mind , 1993 .

[13]  Ron Sun,et al.  Integrating rules and connectionism for robust commonsense reasoning , 1994, Sixth-generation computer technology series.

[14]  Jude W. Shavlik,et al.  Incorporating Advice into Agents that Learn from Reinforcements , 1994, AAAI.

[15]  Ron Sun,et al.  Computational Architectures Integrating Neural And Symbolic Processes , 1994 .

[16]  R. Nosofsky,et al.  Rule-plus-exception model of classification learning. , 1994, Psychological review.

[17]  Ron Sun,et al.  Robust Reasoning: Integrating Rule-Based and Similarity-Based Reasoning , 1995, Artif. Intell..

[18]  Ben J. A. Kröse,et al.  Learning from delayed rewards , 1995, Robotics Auton. Syst..

[19]  K. VanLehn,et al.  Cognitive skill acquisition. , 1996, Annual review of psychology.