2024/02/07 by Lau, Elaine, Lu, Stephen Zhewen, Pan, Ling +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG)
paper · doi:10.48550/arxiv.2402.05234
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.