ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2506.16313
17
0

Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks

19 June 2025
Sajan Muhammad
Salem Lahlou
ArXiv (abs)PDFHTML
Main:5 Pages
6 Figures
Bibliography:3 Pages
2 Tables
Appendix:4 Pages
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.

View on arXiv
@article{muhammad2025_2506.16313,
  title={ Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks },
  author={ Sajan Muhammad and Salem Lahlou },
  journal={arXiv preprint arXiv:2506.16313},
  year={ 2025 }
}
Comments on this paper