Quality-diversity actor-critic: learning high-performing and diverse behaviors via value and successor features critics

L Grillotti, M Faldor, BG León, A Cully - arxiv preprint arxiv:2403.09930, 2024‏ - arxiv.org
A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for
adapting to unexpected situations. Over the past decade, advancements in deep …

Quality-diversity with limited resources

RJ Wang, K Xue, C Guan, C Qian - arxiv preprint arxiv:2406.03731, 2024‏ - arxiv.org
Quality-Diversity (QD) algorithms have emerged as a powerful optimization paradigm with
the aim of generating a set of high-quality and diverse solutions. To achieve such a …

Skill-conditioned policy optimization with successor features representations

L Grillotti, M Faldor, BG León, A Cully - Second Agent Learning in …, 2023‏ - openreview.net
A key aspect of intelligence is the ability to exhibit a wide range of behaviors to adapt to
unforeseen situations. Designing artificial agents that are capable of showcasing a broad …

Extract-QD Framework: A Generic Approach for Quality-Diversity in Noisy, Stochastic or Uncertain Domains

M Flageat, J Huber, F Helenon, S Doncieux… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Quality-Diversity (QD) has demonstrated potential in discovering collections of diverse
solutions to optimisation problems. Originally designed for deterministic environments, QD …

Resolving Goal-Conflicts and Scaling Synthesis through Mode-Based Decomposition

M Brizzio - Proceedings of the 2024 IEEE/ACM 46th International …, 2024‏ - dl.acm.org
Reactive synthesis, with its roots in the work of A. Church, presents a transformative
approach for the formal methods community. It seeks to translate system behaviors …

Benchmark tasks for Quality-Diversity applied to Uncertain domains

M Flageat, L Grillotti, A Cully - … of the Companion Conference on Genetic …, 2023‏ - dl.acm.org
While standard approaches to optimisation focus on producing a single high-performing
solution, Quality-Diversity (QD) algorithms allow large diverse collections of such solutions …

Quality with Just Enough Diversity in Evolutionary Policy Search

P Templier, L Grillotti, E Rachelson, D Wilson… - Proceedings of the …, 2024‏ - dl.acm.org
Evolution Strategies (ES) are effective gradient-free optimization methods that can be
competitive with gradient-based approaches for policy search. ES only rely on the total …