Open-Ended Evolutionary Robotics: an Information Theoretic Approach

Details Open-Ended Evolutionary Robotics: an Information Theoretic Approach Open-Ended Evolutionary Robotics: an Information Theoretic Approach

2010-06-25

arxiv.org/abs/1006.4959v1

PPSN XI, Krakow : Poland (2010)

Computer Science

Robotics

Scientific paper

This paper is concerned with designing self-driven fitness functions for Embedded Evolutionary Robotics. The proposed approach considers the entropy of the sensori-motor stream generated by the robot controller. This entropy is computed using unsupervised learning; its maximization, achieved by an on-board evolutionary algorithm, implements a "curiosity instinct", favouring controllers visiting many diverse sensori-motor states (sms). Further, the set of sms discovered by an individual can be transmitted to its offspring, making a cultural evolution mode possible. Cumulative entropy (computed from ancestors and current individual visits to the sms) defines another self-driven fitness; its optimization implements a "discovery instinct", as it favours controllers visiting new or rare sensori-motor states. Empirical results on the benchmark problems proposed by Lehman and Stanley (2008) comparatively demonstrate the merits of the approach.

Affiliated with

Also associated with

No associations

Rating

Open-Ended Evolutionary Robotics: an Information Theoretic Approach does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Open-Ended Evolutionary Robotics: an Information Theoretic Approach, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Open-Ended Evolutionary Robotics: an Information Theoretic Approach will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-309964