GFlowNets with Human Feedback

Abstract

We propose the GFlowNets with Human Feedback (GFlowHF) framework to improve the exploration ability when training AI models. For tasks where the reward is unknown, we fit the reward function through human evaluations on different trajectories. The goal of GFlowHF is to learn a policy that is strictly proportional to human ratings, instead of only focusing on human favorite ratings like RLHF. Experiments show that GFlowHF can achieve better exploration ability than RLHF.