Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Frontiers in Probabilistic Inference: learning meets Sampling

von Mises-Fisher Sampling of GloVe Vectors

Walid Bendada · Guillaume Salha-Galvan · Romain Hennequin · Théo Bontempelli · Thomas Bouabça · Tristan Cazenave


Abstract:

A recent publication introduced von Mises-Fisher exploration (vMF-exp), a scalable sampling method for exploring large action sets in reinforcement learning problems where hyperspherical embedding vectors represent these actions. We present the first experimental validation of vMF-exp’s key theoretical and scalability properties on a publicly available real-world dataset, confirming the potential of this method.

Chat is not available.