Parametric-Task MAP-Elites - Archive ouverte HAL Access content directly
Conference Papers Year : 2024

Parametric-Task MAP-Elites

Parametric-Task MAP-Elites

Abstract

Optimizing a set of functions simultaneously by leveraging their similarity is called multi-task optimization. Current black-box multi-task algorithms only solve a finite set of tasks, even when the tasks originate from a continuous space. In this paper, we introduce Parametric-task MAP-Elites (PT-ME), a novel black-box algorithm to solve continuous multi-task optimization problems. This algorithm (1) solves a new task at each iteration, effectively covering the continuous space, and (2) exploits a new variation operator based on local linear regression. The resulting dataset of solutions makes it possible to create a function that maps any task parameter to its optimal solution. We show on two parametric-task toy problems and a more realistic and challenging robotic problem in simulation that PT-ME outperforms all baselines, including the deep reinforcement learning algorithm PPO.
Fichier principal
Vignette du fichier
main_arxiv.pdf (6.58 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04532964 , version 1 (04-04-2024)

Licence

Attribution

Identifiers

Cite

Timothée Anne, Jean-Baptiste Mouret. Parametric-Task MAP-Elites. GECCO 2024, Jul 2024, Melbourne, Australia. ⟨10.1145/3638529.3653993⟩. ⟨hal-04532964⟩
35 View
8 Download

Altmetric

Share

Gmail Facebook X LinkedIn More