mlsanityData to 7 Oct 2026

QGFN: Controllable Greediness with Action Values

arXiv 2402.05234 ↗First posted 7 Feb 2024cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate, Q, to create greedier sampling policies which can be controlled by a mixing parameter. We show that several variants of the proposed method, QGFN, are able to improve on the number of high-reward samples generated in a variety of tasks without sacrificing diversity.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 26 of its 38 references that are in the map. First posted on arXiv 7 Feb 2024.

Builds on

26 of 38 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  6. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  7. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  8. 2021GFlowNet Foundationscited by 286
  9. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 244
  10. 2022Biological Sequence Design with GFlowNetscited by 172
  11. 2022Learning GFlowNets from partial episodes for improved convergence and stabilitycited by 129
  12. 2022GFlowNets and variational inferencecited by 103
14 more
  1. 2022Multi-Objective GFlowNetscited by 100
  2. 2023A theory of continuous generative flow networkscited by 98
  3. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 83
  4. 2020AdaLead: A simple and robust adaptive greedy search algorithm for sequence designcited by 63
  5. 2023Generative Flow Networks as Entropy-Regularized RLcited by 60
  6. 2023Local Search GFlowNetscited by 45
  7. 2020Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structurescited by 44
  8. 2023Stochastic Generative Flow Networkscited by 32
  9. 2023Thompson sampling for improved exploration in GFlowNetscited by 31
  10. 2023Maximum entropy GFlowNets with soft Q-learningcited by 30
  11. 2023Learning to Scale Logits for Temperature-Conditional GFlowNetscited by 26
  12. 2022Unifying Generative Models with GFlowNets and Beyondcited by 24
  13. 2023An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNetscited by 17
  14. 2023DGFN: Double Generative Flow Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 4; 2026: 5.

18 papers.

Sort:

By area:

  1. 2024Learning diverse attacks on large language models for robust red-teaming and safety tuningcited by 54
  2. 2024Efficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNetscited by 30
  3. 2024Adaptive teachers for amortized samplerscited by 23
  4. 2025Learning to Sample Effective and Diverse Prompts for Text-to-Image Generationcited by 16
  5. 2024Pessimistic Backward Policy for GFlowNetscited by 13
  6. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximizationcited by 12
  7. 2024Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networkscited by 9
  8. 2024Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNetscited by 8
  9. 2025Revisiting Non-Acyclic GFlowNets in Discrete Environmentscited by 8
  10. 2024Random Policy Evaluation Uncovers Policies of Generative Flow Networkscited by 5
  11. 2024Bifurcated Generative Flow Networkscited by 1
  12. 2025Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Trainingcited by 0
6 more
  1. 2025Planning-Augmented Sampling with Early Guidance for High-Reward Discoverycited by 0
  2. 2026Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectivescited by 0
  3. 2026Exploring Multiple High-Scoring Subspaces in Generative Flow Networkscited by 0
  4. 2026Stable GFlowNets with TV Monitoring and Probabilistic Guaranteescited by 0
  5. 2026Your GFlowNet Secretly Learns an Optimal Transport Plancited by 0
  6. 2026Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmarkcited by 0