Learning from Errors
Juan Enrique Martínez-Legaz, Antoine Soubeyran · RePEc: Research Papers in Economics · 2003
We present a model of learning in which agents learn from errors. If an action turns out to be an error, the agent rejects not only that action but also neighboring actions. We find that, keeping memory of his errors, under mild assumptions an acceptable solution is asymptotically reached. Moreover, one can take advantage of big errors for a faster learning.