Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks

TL;DR

This paper introduces ENN-GFN-Enhanced, a method that combines epistemic neural networks with GFlowNets to improve exploration by better uncertainty estimation, leading to more efficient trajectory discovery.

Contribution

It presents a novel integration of epistemic neural networks with GFlowNets, enhancing uncertainty quantification and exploration capabilities.

Findings

Improved trajectory identification in grid environments.

Enhanced exploration efficiency in structured sequence generation.

Outperforms baseline methods in various settings.

Abstract

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.