More complex environments may be required to discover benefits of lifetime learning in evolving robots

TL;DR

This paper demonstrates that intra-life learning significantly benefits robot evolution in complex, hilly environments, suggesting that challenging settings are necessary to observe the advantages of lifetime learning.

Contribution

It compares the effects of intra-life learning in easy and challenging environments, highlighting the importance of environment complexity for evaluating learning benefits in robot evolution.

Findings

Learning is more beneficial in hilly environments

Challenging environments reveal the advantages of lifetime learning

Simple environments may underestimate learning benefits

Abstract

It is well known that intra-life learning, defined as an additional controller optimization loop, is beneficial for evolving robot morphologies for locomotion. In this work, we investigate this further by comparing it in two different environments: an easy flat environment and a more challenging hills environment. We show that learning is significantly more beneficial in a hilly environment than in a flat environment and that it might be needed to evaluate robots in a more challenging environment to see the benefits of learning.