Guiding Evolutionary Learning by Searching for Regularities in Behavioral Trajectories: A Case for Representation Agnosticism

Citation

Krawiec K & Swan J (2013) Guiding Evolutionary Learning by Searching for Regularities in Behavioral Trajectories: A Case for Representation Agnosticism. In: AAAI Fall Symposium 2013: How Should Intelligence be Abstracted in AI Research. AAAI Technical Report, FS-13-02. AAAI Fall Symposium 2013: How Should Intelligence be Abstracted in AI Research, Arlington, VA, USA, 15.11.2013-17.11.2013. Association for the Advancement of Artificial, pp. 41-46. http://www.aaai.org/ocs/index.php/FSS/FSS13/paper/viewFile/7590/7506

Abstract
An intelligent agent can display behavior that is not directly related to the task it learns. Depending on the adopted AI framework and task formulation, such behavior is sometimes attributed to environment exploration, or ignored as irrelevant, or even penalized as undesired. We postulate here that virtually every interaction of an agent with its learning environment can result in outcomes that carry information which can be potentially exploited to solve the task. To support this claim, we present Pattern Guided Evolutionary Algorithm (PANGEA), an extension of genetic programming (GP), a genre of evolutionary computation that aims at synthesizing programs that display the desired input-output behavior. PANGEA uses machine learning to search for regularities in intermediate outcomes of program execution (which are ignored in standard GP), more specifically for relationships between these outcomes and the desired program output. The information elicited in this way is used to guide the evolutionary learning process by appropriately adjusting program fitness. An experiment conducted on a suite of benchmarks demonstrates that this architecture makes agent learning more effective than in conventional GP. In the paper, we discuss the possible generalizations and extensions of this architecture and its relationships with other contemporary paradigms like novelty search and deep learning. In conclusion, we extrapolate PANGEA to postulate a dynamic and behavioral learning framework for intelligent agents.