Michael Garcia Ortiz — accepted AI-conference papers

2019

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

Hugo Caselles-Dupré, Michael Garcia Ortiz, David Filliat

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…

Cited by 79 Source ↗PDF ↗code ↗Scholar ↗

2019

Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction

Alban Laflaquière, Michael Garcia Ortiz

NeurIPS 2019poster

Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood. Recent theoretical works suggest that the Euclidean structure of space induces invariants in an agent’s raw sensorimotor…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗