Open-Ended Evolutionary Robotics: an Information Theoretic Approach

TL;DR

This paper introduces an information-theoretic approach to evolutionary robotics, using entropy-based fitness functions that promote curiosity and discovery, leading to diverse and innovative robot controllers.

Contribution

It proposes a novel self-driven fitness framework based on sensori-motor entropy maximization and cultural transmission, enhancing exploration in evolutionary robotics.

Findings

Improved exploration of sensori-motor space in benchmark tasks

Demonstrated effectiveness of curiosity-driven evolution

Showed benefits of cultural transmission in controller evolution

Abstract

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.