“Generative flow networks (GFNs) are a class of probabilistic models for sequential sampling of composite objects, proportional to a target distribution that is defined in terms of an energy function or a reward. GFNs are typically trained using a flow matching or trajectory balance objective, which matches forward and backward transition models over trajectories. … We introduce a variational objective for training GFNs, which is a convex combination of the reverse- and forward KL divergences, and compare it to the trajectory balance objective when sampling from the forward- and backward model, respectively.”

Find the paper and full list of authors at OpenReview.