Limits of Lamarckian Evolution Under Pressure of Morphological Novelty

TL;DR

This paper investigates how Lamarckian inheritance in evolving modular robots performs under high morphological diversity, revealing a trade-off between inheritance benefits and diversity-driven exploration.

Contribution

It demonstrates that Lamarckian evolution's advantage diminishes with increased morphological novelty, highlighting fundamental limits in such systems.

Findings

Lamarckian evolution outperforms Darwinian when optimizing for task performance.

Introducing morphological diversity reduces Lamarckian system performance.

Diversity promotion decreases parent-offspring similarity, limiting inheritance benefits.

Abstract

Lamarckian inheritance has been shown to be a powerful accelerator in systems where the joint evolution of robot morphologies and controllers is enhanced with individual learning. Its defining advantage lies in the offspring inheriting controllers learned by their parents. The efficacy of this option, however, relies on morphological similarity between parent and offspring. In this study, we examine how Lamarckian inheritance performs when the search process is driven toward high morphological variance, potentially straining the requirement for parent-offspring similarity. Using a system of modular robots that can evolve and learn to solve a locomotion task, we compare Darwinian and Lamarckian evolution to determine how they respond to shifting from pure task-based selection to a multi-objective pressure that also rewards morphological novelty. Our results confirm that Lamarckian evolution outperforms Darwinian evolution when optimizing task-performance alone. However, introducing selection pressure for morphological diversity causes a substantial performance drop, which is much greater in the Lamarckian system. Further analyses show that promoting diversity reduces parent-offspring similarity, which in turn reduces the benefits of inheriting controllers learned by parents. These results reveal the limits of Lamarckian evolution by exposing a fundamental trade-off between inheritance-based exploitation and diversity-driven exploration.