paper-with-me

Papers

Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration

2023-02-24 · Hannah Janmohamed, Thomas Pierrot, Antoine Cully

Quality-Diversity (QD) algorithms have recently gained traction as optimisation methods due to their effectiveness at escaping local optima and capability of generating wide-ranging and high-performing solutions. Recently, Multi-Objective MAP-Elites (MOME) extended the QD paradigm to the multi-objective setting by maintaining a Pareto front in each cell of a map-elites grid. MOME achieved a global performance that competed with NSGA-II and SPEA2, two well-established Multi-Objective Evolutionary Algorithms (MOEA), while also acquiring a diverse repertoire of solutions. However, MOME is limited by non-directed genetic search mechanisms which struggle in high-dimensional search spaces. In this work, we present Multi-Objective MAP-Elites with Policy-Gradient Assistance and Crowding-based Exploration (MOME-PGX): a new QD algorithm that extends MOME to improve its data efficiency and performance. MOME-PGX uses gradient-based optimisation to efficiently drive solutions towards higher performance. It also introduces crowding-based mechanisms to create an improved exploration strategy and to encourage uniformity across Pareto fronts. We evaluate MOME-PGX in four simulated robot locomotion tasks and demonstrate that it converges faster and to a higher performance than all other baselines. We show that MOME-PGX is between 4.3 and 42 times more data-efficient than MOME and doubles the performance of MOME, NSGA-II and SPEA2 in challenging environments.

📄 PDF Abstract BibTeX arXiv:2302.12668

Code (1)

adaptive-intelligent-robotics/mome_pgx 공식 구현 jax

Tasks

DiversityEvolutionary Algorithms

Similar Papers 제목 키워드 기반

Tackling Neural Architecture Search With Quality Diversity Optimization

2022-07-30 · Lennart Schneider, Florian Pfisterer, Paul Kent, Juergen Branke 외

Neural architecture search (NAS) has been studied extensively and has grown to become a research field with substantial impact. While classical single-objective NAS searches for the architecture with the best performance…

DiversityNeural Architecture Search

Preference-Conditioned Gradient Variations for Multi-Objective Quality-Diversity

2024-11-19 · Hannah Janmohamed, Maxence Faldor, Thomas Pierrot, Antoine Cully

In a variety of domains, from robotics to finance, Quality-Diversity algorithms have been used to generate collections of both diverse and high-performing solutions. Multi-Objective Quality-Diversity algorithms have emer…

Diversity

Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization

2024-11-24 · Biqing Qi, Zhouyi Qian, Yiang Luo, Junqi Gao 외

As multi-modal large language models (MLLMs) are increasingly applied to complex reasoning tasks, the diversity and quality of reasoning paths become crucial factors affecting their performance. Although current methods …

Diversity

Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces

2025-03-28 · Hannah Janmohamed, Antoine Cully

Quality-Diversity algorithms are powerful tools for discovering diverse, high-performing solutions. Recently, Multi-Objective Quality-Diversity (MOQD) extends QD to problems with several objectives while preserving solut…

DiversityImage GenerationProtein Design

Multi-Objective Quality-Diversity for Crystal Structure Prediction

2024-03-25 · Hannah Janmohamed, Marta Wolinska, Shikha Surana, Thomas Pierrot 외

Crystal structures are indispensable across various domains, from batteries to solar cells, and extensive research has been dedicated to predicting their properties based on their atomic configurations. However, prevaili…

DiversityPrediction