Information-Geometric Forward Policy Training in GFlowNets

By Yordan Raykov · Paper · stat.ML

Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward. In this work, we formulate forward-policy training in G

Stat.ml

View original

HomeResourceLoading…