Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning

Model complexity is key concern to any artificial learning system due its critical impact on generalization. However, EC research has only focused phenotype structural complexity for static problems. For sequential decision tasks, phenotypes that are very similar in structure, can produce radically different behaviors, and the trade-off between fitness and complexity in this context is not clear. In this paper, behavioral complexity is measured explicitly using compression, and used as a separate objective to be optimized (not as an additional regularization term in a scalar fitness), in order to study this trade-off directly.

• Type: Conference
• Year: 2009
• Where: ICANN
• Authors: Faustino J. Gomez, Julian Togelius, Jürgen Schmidhuber
• Keywords: Artificial Intelligence, ICANN 2009, Model Complexity, Phenotype Structural Complexity, Sequential Decision Tasks