Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks

Efficiently identifying the right trajectories for training remains an open problemin GFlowNets. To address this, it is essential to prioritize exploration in regions ofthe state space where the reward distribution has not been sufficiently learned. This calls for uncertainty-driven exploration, in other words, the agent should be awareof what it does not know. This attribute can be measured by joint predictions, which are particularly important for combinatorial and sequential decision problems. In this research, we integrate epistemic neural networks (ENN) with the conventional architecture of GFlowNets to enable more efficient joint predictions and better uncertainty quantification, thereby improving exploration and the identification of optimal trajectories. Our proposed algorithm, ENN-GFN-Enhanced, is compared to the baseline method in GFlownets and evaluated in grid environments andstructured sequence generation in various settings, demonstrating both its efficacy and efficiency.