Controllable Exploration of a Design Space via Interactive Quality Diversity
Uložené v:
| Názov: | Controllable Exploration of a Design Space via Interactive Quality Diversity |
|---|---|
| Autori: | Sfikas, Konstantinos, Liapis, Antonios, Yannakakis, Georgios N., Genetic and Evolutionary Computation Conference Companion |
| Zdroj: | Proceedings of the Companion Conference on Genetic and Evolutionary Computation (GECCO '23 Companion) Proceedings of the Companion Conference on Genetic and Evolutionary Computation |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | ACM, 2023. |
| Rok vydania: | 2023 |
| Predmety: | FOS: Computer and information sciences, Computer games -- Design, Artificial intelligence, Pattern recognition, Application software, Computer Science - Human-Computer Interaction, Computer Science - Neural and Evolutionary Computing, Computer communication systems, Evolutionary computation, Neural and Evolutionary Computing (cs.NE), Algorithms, Human-Computer Interaction (cs.HC) |
| Popis: | This paper introduces a user-driven evolutionary algorithm based on Quality Diversity (QD) search. During a design session, the user iteratively selects among presented alternatives and their selections affect the upcoming results. We aim to address two major concerns of interactive evolution: (a) the user must be presented with few alternatives, to reduce cognitive load; (b) presented alternatives should be diverse but similar to the previous user selection, to reduce user fatigue. To address these concerns, we implement a variation of the MAP-Elites algorithm where the presented alternatives are sampled from a small region (window) of the behavioral space. After a user selection, the window is centered on the selected individual's behavior characterization, evolution selects parents from within this window to produce offspring, and new alternatives are sampled. Essentially we define an adaptive system of local QD, where the user's selections guide the search towards specific regions of the behavioral space. The system is tested on the generation of architectural layouts, a constrained optimization task, leveraging QD through a two-archive approach. Results show that while global exploration is not as pronounced as in MAP-Elites, the system finds more appropriate solutions to the user's taste, based on experiments with controllable artificial users. Parts of this manuscripts are published at The Genetic and Evolutionary Computation Conference (GECCO) 2023 |
| Druh dokumentu: | Article Conference object |
| DOI: | 10.1145/3583133.3590616 |
| DOI: | 10.48550/arxiv.2304.01642 |
| Prístupová URL adresa: | http://arxiv.org/abs/2304.01642 https://www.um.edu.mt/library/oar/handle/123456789/121628 |
| Rights: | arXiv Non-Exclusive Distribution URL: https://www.acm.org/publications/policies/copyright_policy#Background |
| Prístupové číslo: | edsair.doi.dedup.....10cd4abbd2e8f642a70df80ffecb68ef |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | This paper introduces a user-driven evolutionary algorithm based on Quality Diversity (QD) search. During a design session, the user iteratively selects among presented alternatives and their selections affect the upcoming results. We aim to address two major concerns of interactive evolution: (a) the user must be presented with few alternatives, to reduce cognitive load; (b) presented alternatives should be diverse but similar to the previous user selection, to reduce user fatigue. To address these concerns, we implement a variation of the MAP-Elites algorithm where the presented alternatives are sampled from a small region (window) of the behavioral space. After a user selection, the window is centered on the selected individual's behavior characterization, evolution selects parents from within this window to produce offspring, and new alternatives are sampled. Essentially we define an adaptive system of local QD, where the user's selections guide the search towards specific regions of the behavioral space. The system is tested on the generation of architectural layouts, a constrained optimization task, leveraging QD through a two-archive approach. Results show that while global exploration is not as pronounced as in MAP-Elites, the system finds more appropriate solutions to the user's taste, based on experiments with controllable artificial users.<br />Parts of this manuscripts are published at The Genetic and Evolutionary Computation Conference (GECCO) 2023 |
|---|---|
| DOI: | 10.1145/3583133.3590616 |