Pith. sign in

REVIEW 1 cited by

Distributional GFlowNets with Quantile Flows

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2302.05793 v3 pith:WRDAQX43 submitted 2023-02-11 cs.LG cs.AIstat.COstat.ML

classification cs.LGcs.AIstat.COstat.ML
keywords distributionalflowgflownetslearningquantilealgorithmfunctiongflownet
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training

    cs.LG 2025-05 conditional novelty 6.0 of 10

    TD-GFN uses IRL-derived edge rewards to prune the environment DAG and sample backward trajectories, training offline GFlowNets directly from ground-truth terminal rewards without a proxy reward model.

Pith tools