AI RESEARCH
Boosted GFlowNets: Improving Exploration via Sequential Learning
arXiv CS.LG
•
ArXi:2511.09677v2 Announce Type: replace Generative Flow Networks (GFlowNets) are powerful samplers for compositional objects that, by design, sample proportionally to a given non-negative reward. Nonetheless, in practice, they often struggle to explore the reward landscape evenly: trajectories toward easy-to-reach regions dominate