Search Results for author: Francisco J. H. Heras

Found 4 papers, 4 papers with code

Automated Discovery of Local Rules for Desired Collective-Level Behavior Through Reinforcement Learning

1 code implementation25 Jul 2020 Tiago Costa, Andres Laan, Francisco J. H. Heras, Gonzalo G. de Polavieja

We obtained this result by using recent advances in reinforcementlearning to systematically solve the inverse modeling problem: given an observedcollective behavior, we automatically find a policy generating it.


Deep attention networks reveal the rules of collective motion in zebrafish

1 code implementation13 Sep 2019 Francisco J. H. Heras, Francisco Romero-Ferrero, Robert C. Hinz, Gonzalo G. de Polavieja

When using simulated trajectories, the model recovers the ground-truth interaction rule used to generate them, as well as the number of interacting neighbours.

Behavioural cloning Deep Attention

Cannot find the paper you are looking for? You can Submit a new open access paper.