Alonso, E., Fairbank, M. and Mondragon, E. (2015). Back to optimality: a formal framework to express the dynamics of learning optimal behavior. Adaptive Behavior, 23(4), pp. 206215. doi: 10.1177/1059712315589355
Abstract
Whether animals behave optimally is an open question of great importance, both theoretically and in practice. Attempts to answer this question focus on two aspects of the optimization problem, the quantity to be optimized and the optimization process itself. In this paper, we assume the abstract concept of cost as the quantity to be minimized and propose a reinforcement learning algorithm, called ValueGradient Learning (VGL), as a computational model of behavior optimality. We prove that, unlike standard models of Reinforcement Learning, Temporal Difference in particular, VGL is guaranteed to converge to optimality under certain conditions. The core of the proof is the mathematical equivalence of VGL and Pontryagin’s Minimum Principle, a wellknown optimization technique in systems and control theory. Given the similarity between VGL’s formulation and regulatory models of behavior, we argue that our algorithm may provide psychologists with a tool to formulate such models in optimization terms.
Publication Type:  Article 

Publisher Keywords:  Optimality; Principle of Least Action; bliss point; reinforcement learning; ValueGradient Learning 
Subjects:  Q Science > QA Mathematics > QA75 Electronic computers. Computer science 
Departments:  School of Mathematics, Computer Science & Engineering > Computer Science 
URI:  http://openaccess.city.ac.uk/id/eprint/12258 

Text
 Accepted Version
Download (966kB)  Preview 
Export
Downloads
Downloads per month over past year
Actions (login required)
Admin Login 