Multi-objective quality diversity optimization

Pierrot, Thomas; Richard, Guillaume; Beguir, Karim; Cully, Antoine

doi:10.1145/3512290.3528823

Cited by 16 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, multi-objective QD could be employed to enable the search for materials with conicting objectives, while discovering large collections of structures that span across the property space. 15 Alternatively, if differentiable models are used for all feature and tness function models, gradients can be used to inform the mutations thus allowing solutions to converge faster. This is done in Differentiable Quality-Diversity.…”

Section: Discussion and Further Workmentioning

confidence: 99%

“…This however can be seen as a limitation, because potentially high-performing solutions that lie outside of this condition would be discarded. 15 Such techniques are also not designed to explicitly provide diverse solutions to a problem, which could aid the user in understanding the feature space of their problem. Materials properties have indeed been used to characterise organic crystal structures in the form of energyfunction-structure maps, with the aim of facilitating structure selection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms

Wolinska,

Walsh,

Cully

2024

Digital Discovery

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussion and Further Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms

Wolinska,

Walsh,

Cully

2024

Digital Discovery

Self Cite

View full text Add to dashboard Cite

show abstract

“…This approach generates significant Quality Diversity, while implicitly overcoming the problem of determining stepping stones or learning curriculum order, as offspring for any given subset of the phenotypic space compete to become the elite in every other cell within the map -constantly goal-switching to find potential stepping stones that may enable them to perform well on other phenotypic subsets [8,16]. Multi-Objective MAP-Elites [18] fills each cell in the behavior map with a Pareto front rather than a single individual. Unlike in our work, each cell corresponds with a unique behavior descriptor and optimizes all objectives simultaneously.…”

mentioning

confidence: 99%

Many-objective Optimization via Voting for Elites

Dean

Cheney

2023

Proceedings of the Companion Conference on Genetic and Evolutionary Computation

View full text Add to dashboard Cite

Real-world problems are often comprised of many objectives and require solutions that carefully trade-off between them. Current approaches to many-objective optimization often require challenging assumptions, like knowledge of the importance/difficulty of objectives in a weighted-sum single-objective paradigm, or enormous populations to overcome the curse of dimensionality in multiobjective Pareto optimization. Combining elements from Many-Objective Evolutionary Algorithms and Quality Diversity algorithms like MAP-Elites, we propose Many-objective Optimization via Voting for Elites (MOVE). MOVE maintains a map of elites that perform well on different subsets of the objective functions. On a 14-objective image-neuroevolution problem, we demonstrate that MOVE is viable with a population of as few as 50 elites and outperforms a naive single-objective baseline. We find that the algorithm's performance relies on solutions jumping across bins (for a parent to produce a child that is elite for a different subset of objectives). We suggest that this type of goal-switching is an implicit method to automatic identification of stepping stones or curriculum learning. We comment on the similarities and differences between MOVE and MAP-Elites, hoping to provide insight to aid in the understanding of that approach -and suggest future work that may inform this approach's use for many-objective problems in general.

show abstract

“…The work by Fontaine et al was expanded into the Multi-Emitter MAP-Elites, improving the quality, diversity, and convergence speed of MAP-Elites in general [127]. Other work within MAP-Elites has focused on its robustness [128], multiobjective tasks optimization [129], or assessing its properties when coupled in interactive environments [130].…”

Section: Quality Diversitymentioning

confidence: 99%

E X P Loring Game De S Ign Through Human-Ai Col Laborat Ion

Alvarez¹

View full text Add to dashboard Cite

Game design is a hard and multi-faceted task that intertwines different gameplay mechanics, audio, level, graphic, and narrative facets. Games' facets are developed in conjunction with others with a common goal that makes games coherent and interesting. These combinations result in plenty of games in diverse genres, which usually require a collaboration of a diverse group of designers. Collaborators can take different roles and support each other with their strengths resulting in games with unique characteristics. The multi-faceted nature of games and their collaborative properties and requirements make it an exciting task to use Artificial Intelligence (AI). The generation of these facets together requires a holistic approach, which is one of the most challenging tasks within computational creativity. Given the collaborative aspect of games, this thesis approaches their generation through Human-AI collaboration, specifically using a mixed-initiative co-creative (MI-CC) paradigm. This paradigm creates an interactive and collaborative scenario that leverages AI and human strengths with an alternating and proactive initiative to approach a task. However, this paradigm introduces several challenges, such as Human and AI goal alignment or competing properties. In this thesis, game design and the generation of game facets by themselves and intertwined are explored through Human-AI collaboration. The AI takes a colleague's role with the designer, arising multiple dynamics, challenges, and opportunities. The main hypothesis is that AI can be incorporated into systems as a collaborator, enhancing design tools, fostering human creativity, and reducing workload. The challenges and opportunities that arise from this are explored, discussed, and approached throughout the thesis. As a result, multiple approaches and methods such as quality-diversity algorithms and designer modeling are proposed to generate game facets in tandem with humans, create a better workflow, enhance the interaction, and establish adaptive experiences.

show abstract

Multi-objective quality diversity optimization

Cited by 16 publications

References 16 publications

Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms

Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms

Many-objective Optimization via Voting for Elites

E X P Loring Game De S Ign Through Human-Ai Col Laborat Ion

Contact Info

Product

Resources

About