Premium
Adding Prediction Risk to the Theory of Reward Learning
Author(s) -
PREUSCHOFF KERSTIN,
BOSSAERTS PETER
Publication year - 2007
Publication title -
annals of the new york academy of sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.712
H-Index - 248
eISSN - 1749-6632
pISSN - 0077-8923
DOI - 10.1196/annals.1390.005
Subject(s) - covariance , reinforcement learning , computer science , machine learning , mean squared prediction error , artificial intelligence , econometrics , mathematics , statistics
This article analyzesthe simple Rescorla–Wagner learning rule from the vantage point of least squares learning theory. In particular, it suggests how measures of risk, such as prediction risk, can be used to adjust the learning constant in reinforcement learning. It argues that prediction risk is most effectively incorporated by scaling the prediction errors. This way, the learning rate needs adjusting only when the covariance between optimal predictions and past (scaled) prediction errors changes. Evidence is discussed that suggests that the dopaminergic system in the (human and nonhuman) primate brain encodes prediction risk, and that prediction errors are indeed scaled with prediction risk (adaptive encoding).