← Search

Hugo Caselles-Dupré

2 accepted papers

2022

Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environments

NeurIPS 2022accept

Learning from demonstration methods usually leverage close to optimal demonstrations to accelerate training. By contrast, when demonstrating a task, human teachers deviate from optimal demonstrations and pedagogically modify their behavior by giving demonstrations that best disambiguate the goal the…

2019

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

NeurIPS 2019poster

Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents. Higgins et al. recently proposed Symmetry-Based Disentangled Representation Le…