Novelty Search in Competitive Coevolution
This addresses convergence issues in coevolutionary algorithms for researchers in evolutionary computation, though it is incremental as it adapts novelty search to a known bottleneck.
The paper tackled the problem of premature convergence in competitive coevolution by investigating novelty search to sustain arms races, resulting in significantly more diverse solutions in a predator-prey task compared to traditional fitness-based methods.
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.