Olivier Bachem

TL;DR: The authors show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data, and suggest that future work on disentanglement learning should be explicit about the role of inductive bias and (implicit) supervision.

TL;DR: An in-depth review of recent advances in representation learning with a focus on autoencoder-based models and makes use of meta-priors believed useful for downstream tasks, such as disentanglement and hierarchical organization of features.

TL;DR: This work presents the Visual Task Adaptation Benchmark (VTAB), which defines good representations as those that adapt to diverse, unseen tasks with few examples, and addresses questions like: How effective are ImageNet representations beyond standard natural datasets?

TL;DR: This work theoretically shows that only knowing how many factors have changed, but not which ones, is sufficient to learn disentangled representations, and provides practical algorithms that learn disENTangled representations from pairs of images without requiring annotation of groups, individual factors, or the number of factors that have changed.

TL;DR: The Google Research Football Environment as discussed by the authors is a 3D simulation environment where agents are trained to play football in an advanced, physics-based 3D simulator and the resulting environment is challenging, easy to use and customize, and it provides support for multiplayer and multi-agent experiments.