Surrogate-based quantification of policy uncertainty in generative flow networks

• URL: http://arxiv.org/abs/2510.21523v1
• Date: Fri, 24 Oct 2025 14:44:36 GMT
• Title: Surrogate-based quantification of policy uncertainty in generative flow networks
• Authors: Ramón Nartallo-Kaluarachchi, Robert Manson-Sawko, Shashanka Ubaru, Dongsung Huh, Małgorzata J Zimoń, Lior Horesh, Yoshua Bengio,
• Abstract summary: We present an approach to quantify uncertainty by constructing a surrogate model.<n>This model learns the relationship between reward functions, parametrised in a low-dimensional space.<n>It can then be used for inexpensive Monte Carlo sampling to estimate the uncertainty in the policy given uncertain rewards.
• Score: 45.21976249692826
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative flow networks are able to sample, via sequential construction, high-reward, complex objects according to a reward function. However, such reward functions are often estimated approximately from noisy data, leading to epistemic uncertainty in the learnt policy. We present an approach to quantify this uncertainty by constructing a surrogate model composed of a polynomial chaos expansion, fit on a small ensemble of trained flow networks. This model learns the relationship between reward functions, parametrised in a low-dimensional space, and the probability distributions over actions at each step along a trajectory of the flow network. The surrogate model can then be used for inexpensive Monte Carlo sampling to estimate the uncertainty in the policy given uncertain rewards. We illustrate the performance of our approach on a discrete and continuous grid-world, symbolic regression, and a Bayesian structure learning task.

Related papers

• Statistical analysis of Inverse Entropy-regularized Reinforcement Learning [15.054399128586232]
  Inverse reinforcement learning aims to infer the reward function that explains expert behavior observed through trajectories of state--action pairs.<n>Many reward functions can induce the same optimal policy, rendering the inverse problem ill-posed.<n>We develop a statistical framework for Inverse Entropy-regularized Reinforcement Learning.
  arXiv  Detail & Related papers  (2025-12-07T18:26:19Z)
• Adaptive Machine Learning-Driven Multi-Fidelity Stratified Sampling for Failure Analysis of Nonlinear Stochastic Systems [0.0]
  We introduce a multi-fidelity stratified sampling scheme with adaptive machine learning metamodels for estimating small failure probabilities.<n>A high-fidelity dataset is used to train a deep learning-based metamodel, which then serves as a cost-effective and highly correlated low-fidelity model.<n>An unbiased estimate of the strata-wise failure probabilities is obtained using a multi-fidelity Monte Carlo framework.
  arXiv  Detail & Related papers  (2025-08-01T16:04:21Z)
• Robust Optimization with Diffusion Models for Green Security [49.68562792424776]
  In green security, defenders must forecast adversarial behavior, such as poaching, illegal logging, and illegal fishing, to plan effective patrols.<n>We propose a conditional diffusion model for adversary behavior modeling, leveraging its strong distribution-fitting capabilities.<n>We introduce a mixed strategy of mixed strategies and employ a twisted Sequential Monte Carlo (SMC) sampler for accurate sampling.
  arXiv  Detail & Related papers  (2025-02-19T05:30:46Z)
• Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Data [2.6499018693213316]
  We introduce a novel generative model for the representation of joint probability distributions of discrete random variables.<n>The approach uses measure transport by randomized assignment flows on the statistical submanifold of factorizing distributions.
  arXiv  Detail & Related papers  (2024-06-06T21:58:33Z)
• Implicit Variational Inference for High-Dimensional Posteriors [7.924706533725115]
  In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors. Our approach introduces novel bounds for approximate inference using implicit distributions by locally linearising the neural sampler.
  arXiv  Detail & Related papers  (2023-10-10T14:06:56Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Distributional GFlowNets with Quantile Flows [73.73721901056662]
  Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
  arXiv  Detail & Related papers  (2023-02-11T22:06:17Z)
• Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks [71.95722100511627]
  We consider the off-policy evaluation problem of reinforcement learning using deep neural networks. We show that, by choosing network size appropriately, one can leverage the low-dimensional manifold structure in the Markov decision process.
  arXiv  Detail & Related papers  (2022-06-06T20:25:20Z)
• Implicit Distributional Reinforcement Learning [61.166030238490634]
  implicit distributional actor-critic (IDAC) built on two deep generator networks (DGNs) Semi-implicit actor (SIA) powered by a flexible policy distribution. We observe IDAC outperforms state-of-the-art algorithms on representative OpenAI Gym environments.
  arXiv  Detail & Related papers  (2020-07-13T02:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.