# Improved Exploration in GFlownets via Enhanced Epistemic Neural Networks

arXiv: https://arxiv.org/abs/2506.16313 · HTML: https://mlsanity.com/paper/2506.16313/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 30 references that are in the map.
- First posted on arXiv 19 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [Teacher-Student Curriculum Learning](https://mlsanity.com/paper/1707.00183/) (2017)
- [Learning GFlowNets from partial episodes for improved convergence and stability](https://mlsanity.com/paper/2209.12782/) (2022)
- [Epistemic Neural Networks](https://mlsanity.com/paper/2107.08924/) (2021)
- [GFlowNets and variational inference](https://mlsanity.com/paper/2210.00580/) (2022)
- [DEUP: Direct Epistemic Uncertainty Prediction](https://mlsanity.com/paper/2102.08501/) (2021)
- [Multi-Objective GFlowNets](https://mlsanity.com/paper/2210.12765/) (2022)
- [A theory of continuous generative flow networks](https://mlsanity.com/paper/2301.12594/) (2023)
- [Amortizing intractable inference in large language models](https://mlsanity.com/paper/2310.04363/) (2023)
- [Better Training of GFlowNets with Local Credit and Incomplete Trajectories](https://mlsanity.com/paper/2302.01687/) (2023)
- [Towards Understanding and Improving GFlowNet Training](https://mlsanity.com/paper/2305.07170/) (2023)
- [Generative Augmented Flow Networks](https://mlsanity.com/paper/2210.03308/) (2022)
- [Thompson sampling for improved exploration in GFlowNets](https://mlsanity.com/paper/2306.17693/) (2023)
- [Approximate Thompson Sampling via Epistemic Neural Networks](https://mlsanity.com/paper/2302.09205/) (2023)
- [From Predictions to Decisions: The Importance of Joint Predictive Distributions](https://mlsanity.com/paper/2107.09224/) (2021)
- [CFlowNets: Continuous Control with Generative Flow Networks](https://mlsanity.com/paper/2303.02430/) (2023)
- [torchgfn: A PyTorch GFlowNet library](https://mlsanity.com/paper/2305.14594/) (2023)
- [Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets](https://mlsanity.com/paper/2504.19981/) (2025)
- [Mastering Rate based Curriculum Learning](https://mlsanity.com/paper/2008.06456/) (2020)
- [Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets](https://mlsanity.com/paper/2505.15251/) (2025)
- [Exploration via Epistemic Value Estimation](https://mlsanity.com/paper/2303.04012/) (2023)
- [BatchGFN: Generative Flow Networks for Batch Active Learning](https://mlsanity.com/paper/2306.15058/) (2023)

## Built on by (most cited first, 1 of 1)

- [Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces](https://mlsanity.com/paper/2602.05961/) (2026)

## Abstract (arXiv)

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.