124 citations · 335 across the 17 of their papers we have counts for
4 papers · 1 filter
Discovering Unsupervised Behaviours from Full-State Trajectories
Luca Grillotti, Antoine Cully
Improving open-ended learning capabilities is a promising approach to enable robots to face the unbounded complexity of the real-world. Among existing methods, the ability of Quali…
Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution
Nemanja Rakicevic, Antoine Cully, Petar Kormushev
Neuroevolution is an alternative to gradient-based optimisation that has the potential to avoid local minima and allows parallelisation. The main limiting factor is that usually it…
Policy Manifold Search for Improving Diversity-based Neuroevolution
Nemanja Rakicevic, Antoine Cully, Petar Kormushev
Diversity-based approaches have recently gained popularity as an alternative paradigm to performance-based policy search. A popular approach from this family, Quality-Diversity (QD…
MAGAN: Margin Adaptation for Generative Adversarial Networks
Ruohan Wang, Antoine Cully, Hyung Jin Chang +1
We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adapti…