arXiv stat.ML
· Papers
Information-Geometric Forward Policy Training in GFlowNets
arXiv:2608.03967v1 Announce Type: new Abstract: 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 train