Artificial curiosity based on discovering novel algorithmic predictability through coevolution

  • Schmidhuber J
  • 34

    Readers

    Mendeley users who have this article in their library.
  • 18

    Citations

    Citations of this article.

Abstract

One explores a spatio-temporal domain by predicting and learning
from success/failure what's predictable and what's not. The author
studies a “curious” embedded agent that differs from
previous explorers in the sense that it can limit its predictions to
fairly arbitrary, computable aspects of event sequences and thus can
explicitly ignore almost arbitrary unpredictable, random aspects. It
constructs initially random algorithms mapping event sequences to
abstract internal representations (IRs). It also constructs algorithms
predicting IRs from IRs computed earlier. It wants to learn novel
algorithms creating IRs useful for correct IR predictions, without
wasting time on those learned before. This is achieved by a
co-evolutionary scheme involving two competing modules co-evolutionary
designing single algorithms to be executed. The modules can bet on the
outcome of IR predictions computed by the algorithms they have agreed
upon. If their opinions differ then the system checks who's right,
punishes the loser (the surprised one), and rewards the winner. A
reinforcement learning algorithm forces each module to maximise reward.
This motivates both modules to lure the other into agreeing upon
algorithms involving predictions that surprise it. Since each module
essentially can put in its veto against algorithms it does not consider
profitable, the system is motivated to focus on those computable aspects
of the environment where both modules still have confident but different
opinions. Once both share the same opinion on a particular issue, the
winner loses a source of reward-an incentive to shift the focus of
interest onto novel, yet unknown algorithms

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Jürgen Schmidhuber

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free