Learning from Errors

Research, Preprint English OPEN
Martínez-Legaz, Juan-Enrique; Soubeyran, Antoine;
  • Identifiers: handle: 10261/1810
  • Subject: Best reply functions | Normal form games | Anàlisi d'error (Matemàtica) | Learning, errors, fixed points, normal form games, best reply functions | Fixed points | Learning | Errors
    • jel: jel:D83 | jel:C72
    arxiv: Computer Science::Machine Learning

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 asy... View more
Share - Bookmark