32 citations · 72 across the 9 of their papers we have counts for
3 papers · 1 filter
PASTA: Pretrained Action-State Transformer Agents
Raphael Boige, Yannis Flet-Berliac, Arthur Flajolet +2
Self-supervised learning has brought about a revolutionary paradigm shift in various computing domains, including NLP, vision, and biology. Recent approaches involve pre-training t…
Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces
Raphael Boige, Guillaume Richard, Jérémie Dona +2
Quality Diversity (QD) algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set of local optima. While e…
The Quality-Diversity Transformer: Generating Behavior-Conditioned Trajectories with Decision Transformers
Valentin Macé, Raphaël Boige, Felix Chalumeau +3
In the context of neuroevolution, Quality-Diversity algorithms have proven effective in generating repertoires of diverse and efficient policies by relying on the definition of a b…