Curiosity-driven optimization

Tom Schaul, Yi Sun, Daan Wierstra, Fausino Gomez, Jurgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

The principle of artificial curiosity directs active exploration towards the most informative or most interesting data. We show its usefulness for global black box optimization when data point evaluations are expensive. Gaussian process regression is used to model the fitness function based on all available observations so far. For each candidate point this model estimates expected fitness reduction, and yields a novel closed-form expression of expected information gain. A new type of Pareto-front algorithm continually pushes the boundary of candidates not dominated by any other known data according to both criteria, using multi-objective evolutionary search. This makes the exploration-exploitation trade-off explicit, and permits maximally informed data selection. We illustrate the robustness of our approach in a number of experimental scenarios. © 2011 IEEE.
Original languageEnglish (US)
Title of host publication2011 IEEE Congress of Evolutionary Computation, CEC 2011
Pages1343-1349
Number of pages7
DOIs
StatePublished - Aug 29 2011
Externally publishedYes

Cite this