Towards Directed Open-Ended Search by a Novelty Guided Evolution Strategy

Graening, Lars; Aulig, Nikola; Olhofer, Markus

doi:10.1007/978-3-642-15871-1_8

Cited by 5 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benefits of divergent search were further confirmed through similar experiments by Mouret and Doncieux (2009) and Mouret and Doncieux (2012), who use the synonymous term behavioral diversity. These initial studies were followed by a wave of interest in divergent search algorithms as researchers explored their potential for discovery and open-endedness (Risi et al, 2009(Risi et al, , 2011Soltoggio and Jones, 2009;Doucette and Heywood, 2010;Goldsby and Cheng, 2010;Graening et al, 2010;Krcah, 2010;Kistemaker and Whiteson, 2011;Woolley and Stanley, 2011;Liapis et al, 2013a,b;Martinez et al, 2013;Morse et al, 2013;Naredo and Trujillo, 2013;Risi and Stanley, 2013). However, a clear missing ingredient from pure novelty or behavioral diversity techniques is a complementary notion of objective quality.…”

Section: Early Divergent Search Algorithmsmentioning

confidence: 99%

Quality Diversity: A New Frontier for Evolutionary Computation

2016

View full text Add to dashboard Cite

While evolutionary computation and evolutionary robotics take inspiration from nature, they have long focused mainly on problems of performance optimization. Yet, evolution in nature can be interpreted as more nuanced than a process of simple optimization. In particular, natural evolution is a divergent search that optimizes locally within each niche as it simultaneously diversifies. This tendency to discover both quality and diversity at the same time differs from many of the conventional algorithms of machine learning, and also thereby suggests a different foundation for inferring the approach of greatest potential for evolutionary algorithms. In fact, several recent evolutionary algorithms called quality diversity (QD) algorithms (e.g., novelty search with local competition and MAP-Elites) have drawn inspiration from this more nuanced view, aiming to fill a space of possibilities with the best possible example of each type of achievable behavior. The result is a new class of algorithms that return an archive of diverse, high-quality behaviors in a single run. The aim in this paper is to study the application of QD algorithms in challenging environments (in particular complex mazes) to establish their best practices for ambitious domains in the future. In addition to providing insight into cases when QD succeeds and fails, 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.

show abstract

Section: Early Divergent Search Algorithmsmentioning

confidence: 99%

Quality Diversity: A New Frontier for Evolutionary Computation

2016

View full text Add to dashboard Cite

show abstract

“…This is, for example, done by relying on novelty alone to select relevant solutions and steer the optimization into the desired direction [12], by combining novelty and a local competition factor of the considered solutions [13], or restarting the optimization based on a novelty-score [14]. Furthermore, additional derived measures such as the interestingness [15,16] or the curiosity [17] can be considered in addition to performance criteria.…”

Section: Optimization-based Approachesmentioning

confidence: 99%

Concept Identification for Complex Engineering Datasets

Lanfermann¹,

Schmitt²

2022

Preprint

View full text Add to dashboard Cite

Finding meaningful concepts in engineering application datasets which allow for a sensible grouping of designs is very helpful in many contexts. It allows for determining different groups of designs with similar properties and provides useful knowledge in the engineering decision making process. Also, it opens the route for further refinements of specific design candidates which exhibit certain characteristic features. In this work, an approach to define meaningful and consistent concepts in an existing engineering dataset is presented. The designs in the dataset are characterized by a multitude of features such as design parameters, geometrical properties or performance values of the design for various boundary conditions. In the proposed approach the complete feature set is partitioned into several subsets called description spaces. The definition of the concepts respects this partitioning which leads to several desired properties of the identified concepts, which cannot be achieved with state-of-the-art clustering or concept identification approaches. A novel concept quality measure is proposed, which provides an objective value for a given definition of concepts in a dataset. The usefulness of the measure is demonstrated by considering a realistic engineering dataset consisting of about 2500 airfoil profiles where the performance values (lift and drag) for three different operating conditions were obtained by a computational fluid dynamics simulation. A numerical optimization procedure is employed which maximizes the concept quality measure, and finds meaningful concepts for different setups of the description spaces while also incorporating user preference. It is demonstrated how these concepts can be used to select archetypal representatives of the dataset which exhibit characteristic features of each concept.

show abstract

“…Historically, a small community within the field of artificial life (Brant & Stanley, 2017;Graening et al, 2010;Langdon, 2005;Lehman & Stanley, 2008;Ray, 1991;Soros & Stanley, 2014;Soros et al, 2016;Standish, 2003b;Stanley et al, 2017;Taylor et al, 2016) has studied the prospects of openended computation for many years. In the ongoing multipronged quest in pursuit of powerful AI, open-endedness is a critical prong: it could serve to generate training environments for meta-learning algorithms (Duan et al, 2016;Finn et al, 2017;Wang et al, 2016), and eventually act as a stepping stone towards AI-generating algorithms (AI-GAs) that could one day bootstrap themselves from simple initial conditions to powerful cognitive machines.…”

Section: Related Workmentioning

confidence: 99%

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

Wang,

Lehman,

Rawal

et al. 2020

Preprint

View full text Add to dashboard Cite

Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. However, the original POET was unable to demonstrate its full creative potential because of limitations of the algorithm itself and because of external issues including a limited problem space and lack of a universal progress measure. Importantly, both limitations pose impediments not only for POET, but for the pursuit of open-endedness in general. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. Together, these four advances enable the most open-ended algorithmic demonstration to date. The algorithmic innovations are (1) a domain-general measure of how meaningfully novel new challenges are, enabling the system to potentially create and solve interesting challenges endlessly, and (2) an efficient heuristic for determining when agents should goal-switch from one problem to another (helping open-ended search better scale). Outside the algorithm itself, to enable a more definitive demonstration of openendedness, we introduce (3) a novel, more flexible way to encode environmental challenges, and (4) a generic measure of the extent to which a system continues to exhibit open-ended innovation. Enhanced POET produces a diverse range of sophisticated behaviors that solve a wide range of

show abstract

Towards Directed Open-Ended Search by a Novelty Guided Evolution Strategy

Cited by 5 publications

References 11 publications

Quality Diversity: A New Frontier for Evolutionary Computation

Quality Diversity: A New Frontier for Evolutionary Computation

Concept Identification for Complex Engineering Datasets

Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

Contact Info

Product

Resources

About