Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks
This work addresses exploration inefficiencies in GFlowNets for combinatorial and sequential decision problems, representing an incremental improvement over existing methods.
The paper tackled the problem of inefficient exploration in GFlowNets by integrating epistemic neural networks to improve uncertainty quantification and joint predictions, resulting in enhanced exploration and identification of optimal trajectories in grid environments and structured sequence generation.
Efficiently identifying the right trajectories for training remains an open problem in GFlowNets. To address this, it is essential to prioritize exploration in regions of the state space where the reward distribution has not been sufficiently learned. This calls for uncertainty-driven exploration, in other words, the agent should be aware of 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 and structured sequence generation in various settings, demonstrating both its efficacy and efficiency.