Constructivist Anticipatory Learning Mechanism ( CALM ) – dealing with partially deterministic and partially observable environments

This paper presents CALM (Constructivist Anticipatory Learning Mechanism), an agent learning mechanism based on a constructivist approach. It is designed to deal dynamically and interactively with environments which are at the same time partially deterministic and partially observable. We describe in detail the mechanism, explaining how it represents knowledge, and how the learning methods operate. We analyze the kinds of environmental regularities that CALM can discover, trying to show that our proposition follows the way towards the construction of more abstract or high-level representational concepts.

[1]  Filipo Studzinski Perotto,et al.  Incremental Inductive Learning in a Constructivist Agent , 2006, SGAI Conf..

[2]  Chris Thornton.  Indirect sensing through abstractive learning , 2003, Intell. Data Anal..

[3]  Charles Lee Isbell,et al.  Schema Learning: Experience-Based Construction of Predictive Action Models , 2004, NIPS.

[4]  Risto Miikkulainen,et al.  The constructivist learning architecture: a model of cognitive development for robust autonomous robots , 2004 .

[5]  L. Suchman.  Plans and situated actions , 1987 .

[6]  Charles Lee Isbell,et al.  Looping suffix tree-based inference of partially observable hidden state , 2006, ICML.

[7]  Marco C. Bettoni,et al.  Made-Up Minds: A Constructivist Approach to Artificial Intelligence , 1993, IEEE Expert.

[8]  Paul A. Crook,et al.  Learning in a State of Confusion: Perceptual Aliasing in Grid World Navigation , 2003 .

[9]  Pat Langley,et al.  Selection of Relevant Features and Examples in Machine Learning , 1997, Artif. Intell..

[10]  J. Piaget.  The construction of reality in the child , 1954 .

[11]  Ronald L. Rivest,et al.  Diversity-based inference of finite automata , 1994, 28th Annual Symposium on Foundations of Computer Science (sfcs 1987).

[12]  T. Oates,et al.  Grounding the Unobservable in the Observable: The Role and Representation of Hidden State in Concept Formation and Refinement , 2001 .

[13]  Peter Stone,et al.  Learning Predictive State Representations , 2003, ICML.

[14]  Andreas Birk,et al.  Schemas and Genetic Programming , 2000 .