Multi-Task Multi-Behavior MAP-Elites - Inria - Institut national de recherche en sciences et technologies du numérique
Conference Papers Year : 2023

Multi-Task Multi-Behavior MAP-Elites

Abstract

We propose Multi-Task Multi-Behavior MAP-Elites, a variant of MAP-Elites that finds a large number of high-quality solutions for a large set of tasks (optimization problems from a given family). It combines the original MAP-Elites for the search for diversity and Multi-Task MAP-Elites for leveraging similarity between tasks. It performs better than three baselines on a humanoid fault-recovery set of tasks, solving more tasks and finding twice as many solutions per solved task.
Fichier principal
Vignette du fichier
HAL_multi_task_multi_behavior_MAP_Elites.pdf (2.9 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

hal-04086519 , version 1 (02-05-2023)

Licence

Identifiers

Cite

Timothee Anne, Jean-Baptiste Mouret. Multi-Task Multi-Behavior MAP-Elites. GECCO '23 Companion: Proceedings of the Companion Conference on Genetic and Evolutionary Computation, 2023, Lisbon, Portugal, France. ⟨10.1145/3583133.3590730⟩. ⟨hal-04086519⟩
51 View
67 Download

Altmetric

Share

More