Novelty Search in Competitive Coevolution

TL;DR

This paper explores how applying novelty search to competitive coevolution can enhance behavioral diversity and prevent premature convergence, demonstrated through a predator-prey pursuit task.

Contribution

It introduces three methods for integrating novelty search into coevolutionary systems and evaluates their effectiveness in promoting diverse solutions.

Findings

Novelty-based methods produce more diverse solutions.

They outperform traditional fitness-based coevolution in diversity.

Methods successfully sustain arms races in coevolution.

Abstract

One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty; (ii) score one population according to novelty, and the other according to fitness; and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when compared to traditional fitness-based coevolution.