Corpus ID: 235458088

Selecting for Selection: Learning To Balance Adaptive and Diversifying Pressures in Evolutionary Search

@article{Frans2021SelectingFS,
  title={Selecting for Selection: Learning To Balance Adaptive and Diversifying Pressures in Evolutionary Search},
  author={Kevin Frans and L. Soros and O. Witkowski},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.09153}
}
Inspired by natural evolution, evolutionary search algorithms have proven remarkably capable due to their dual abilities to radiantly explore through diverse populations and to converge to adaptive pressures. A large part of this behavior comes from the selection function of an evolutionary algorithm, which is a metric for deciding which individuals survive to the next generation. In deceptive or hard-to-search fitness landscapes, greedy selection often fails, thus it is critical that selection… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 28 REFERENCES
Quality Diversity: A New Frontier for Evolutionary Computation
TLDR
A new approach is investigated that hybridizes multiple views of behaviors (called behavior characterizations) in the same run, which succeeds in overcoming some of the challenges associated with searching for QD with respect to a behavior characterization that is not necessarily sufficient for generating both quality and diversity at the same time. Expand
Evolving a diversity of virtual creatures through novelty search and local competition
TLDR
The results in an experiment evolving locomoting virtual creatures show that novelty search with local competition discovers more functional morphological diversity within a single run than models with global competition, which are more predisposed to converge. Expand
Evolvability ES: scalable and direct optimization of evolvability
TLDR
The insight is that it is possible to derive a novel objective in the spirit of natural evolution strategies that maximizes the diversity of behaviors exhibited when an individual is subject to random mutations, and that efficiently scales with computation. Expand
Evolvability Search: Directly Selecting for Evolvability in order to Study and Produce It
TLDR
Evolvability Search enables generating evolvability more easily and directly, facilitating its study and understanding, and may inspire future practical algorithms that increase evolVability without significant computational overhead. Expand
Minimal criterion coevolution: a new approach to open-ended search
TLDR
This paper investigates the extent to which interactions between two coevolving populations, both subject to their own constraint, or minimal criterion, can produce results that are both functional and diverse even without any behavior characterization or novelty archive. Expand
Abandoning Objectives: Evolution Through the Search for Novelty Alone
TLDR
In the maze navigation and biped walking tasks in this paper, novelty search significantly outperforms objective-based search, suggesting the strange conclusion that some problems are best solved by methods that ignore the objective. Expand
Learning behaviour-performance maps with meta-evolution
TLDR
A new meta-evolution algorithm is introduced that discovers those behavioural features that maximise future adaptations in a population of behaviour-performance maps to maximise a meta-fitness function that rewards adaptation. Expand
Death and Progress: How Evolvability is Influenced by Intrinsic Mortality
TLDR
It is indicated that the intrinsic mortality rate and mutation rate induce random genetic drift that allows a population to efficiently traverse a deceptive fitness landscape and supports the premise that programmed death of individuals could have a beneficial effect on the evolvability of the entire population. Expand
Designing neural networks through neuroevolution
TLDR
This Review looks at several key aspects of modern neuroevolution, including large-scale computing, the benefits of novelty and diversity, the power of indirect encoding, and the field’s contributions to meta-learning and architecture search. Expand
Evolvability in grammatical evolution
TLDR
Results suggest that there is not a single factor determining GE evolvability: in particular, the mapping function alone does not deliver better evolVability regardless of the problem, and GE redundancy, which itself is the result of the combined effect of several factors, has a strong impact on the evolviability. Expand
...
1
2
3
...