paper-with-me

홈 › Papers

Distributional GFlowNets with Quantile Flows

2023-02-11 · Dinghuai Zhang, Ling Pan, Ricky T. Q. Chen, Aaron Courville, Yoshua Bengio

Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a stochastic policy for generating complex combinatorial structure through a series of decision-making steps. Despite being inspired from reinforcement learning, the current GFlowNet framework is relatively limited in its applicability and cannot handle stochasticity in the reward function. 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. By parameterizing each edge flow through their quantile functions, our proposed \textit{quantile matching} GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty. Moreover, we find that the distributional approach can achieve substantial improvement on existing benchmarks compared to prior methods due to our enhanced training algorithm, even in settings with deterministic rewards.

📄 PDF Abstract BibTeX arXiv:2302.05793

Code (1)

zdhnarsil/distributional-gflownets 공식 구현 pytorch

Tasks

Decision Making

Similar Papers 제목 키워드 기반

On Learning the Tail Quantiles of Driving Behavior Distributions via Quantile Regression and Flows

2023-05-22 · Jia Yu Tee, Oliver De Candido, Wolfgang Utschick, Philipp Geiger

Towards safe autonomous driving (AD), we consider the problem of learning models that accurately capture the diversity and tail quantiles of human driver behavior probability distributions, in interaction with an AD vehi…

Autonomous DrivingDiversityquantile regressionregression

DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training

2026-02-05 · Dingwei Zhu, Zhiheng Xi, Shihan Dou, Jiahan Li 외 arxiv

Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM post-training. Recent distributional RL …

Reinforcement Learning

Quantile Geometry Regularization for Distributional Reinforcement Learning

2026-05-05 · Zhaofan Zhang, Minghao Yang, Rufeng Chen, Sihong Xie 외 arxiv

Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce distorted or degenerate distribution estimat…

Reinforcement LearningAtari Games

GFlowState: Visualizing the Training of Generative Flow Networks Beyond the Reward

2026-04-23 · Florian Holeczek, Andreas Hinterreiter, Alex Hernandez-Garcia, Marc Streit 외 arxiv

We present GFlowState, a visual analytics system designed to illuminate the training process of Generative Flow Networks (GFlowNets or GFNs). GFlowNets are a probabilistic framework for generating samples proportionally …

Bifurcated Generative Flow Networks

2024-06-04 · Chunhui Li, Cheng-Hao Liu, Dianbo Liu, Qingpeng Cai 외

Generative Flow Networks (GFlowNets), a new family of probabilistic samplers, have recently emerged as a promising framework for learning stochastic policies that generate high-quality and diverse objects proportionally …