Saved in:
Bibliographic Details
Main Authors: Lau, Elaine, Lu, Stephen Zhewen, Pan, Ling, Precup, Doina, Bengio, Emmanuel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.05234
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate, $Q$, to create greedier sampling policies which can be controlled by a mixing parameter. We show that several variants of the proposed method, QGFN, are able to improve on the number of high-reward samples generated in a variety of tasks without sacrificing diversity.