multi-objective optimization

moostral is a fine-tuning on Mistral 7B with the goal of translating multi-objective optimization problems from a textual representation to a jMetal implementation automatically.

SyntheticAI is an LLM-powered synthetic problem generator for multi-objective optimization using OpenAI's APIs for the jMetal and PlatEMO frameworks.

Evolver is a tool based on the formulation of the automatic configuration and design of multi-objective metaheuristics as a multi-objective optimization problem.

Build polynomial models from regression coefficients and optimize them using desirability functions and basin-hopping.

Stage de fin d'étude sur le développement d'un modèle d'apprentissage par renforcement multi-objectifs pour répondre à des problèmes éthiques.

Encadrants : Aurélie Beynier, Nicolas Maudet, Paolo Viappiani Date : Mars - Septembre 2022