Similar to TrajectoryBasedGFlowNet, which is the superclass of TB, SubTB, and LogZVar GFlowNets, meaning that the loss function decomposes into a sum of losses over trajectories, we might need to have two more useful abstractions, as mentioned in the Foundations paper:
EdgeBasedGFlowNet and StateBasedGFlowNet
Similar to
TrajectoryBasedGFlowNet
, which is the superclass of TB, SubTB, and LogZVar GFlowNets, meaning that the loss function decomposes into a sum of losses over trajectories, we might need to have two more useful abstractions, as mentioned in the Foundations paper:EdgeBasedGFlowNet
andStateBasedGFlowNet