Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training 事件

Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training arXiv:2505.20110v3 Announce Type: replace-cross Abstract: Generative Flow Networks (GFlowNets) excel at sampling diverse, high-reward objects. In many practical applications where active reward queries are infeasible, these models must be trained using static offline datasets. Prevailing training methods typically rely on a proxy model to provide reward feedback for online sampled trajectories. However, constructing a