3 papers
cs.LG2021
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…
cs.LG2020
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…
cs.CV2019
Sim-to-Real Learning for Casualty Detection from Ground Projected Point Cloud Data
Roni Permana Saputra, Nemanja Rakicevic, Petar Kormushev
This paper addresses the problem of human body detection---particularly a human body lying on the ground (a.k.a. casualty)---using point cloud data. This ability to detect a casual…