mlsanityData to 14 Oct 2026

WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation

arXiv 2603.17301 ↗First posted 18 Mar 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Generative Flow Networks for continuous scenarios (CFlowNets) have shown promise in solving sequential decision-making tasks by learning stochastic policies using a flow and a retrieval network. Despite their demonstrated efficiency compared to state-of-the-art Reinforcement Learning (RL) algorithms, their practical application in robotic control tasks is constrained by the reliance on pre-training the retrieval network. This dependency poses challenges in dynamic robotic environments, where pre-training data may not be readily available or representative of the current environment. This paper introduces WINFlowNets, a novel CFlowNets framework that enables the co-training of flow and retrieval networks. WINFlowNets begins with a warm-up phase for the retrieval network to bootstrap its policy, followed by a shared training architecture and a shared replay buffer for co-training both networks. Experiments in simulated robotic environments demonstrate that WINFlowNets surpasses CFlowNets and state-of-the-art RL algorithms in terms of average reward and training stability. Furthermore, WINFlowNets exhibits strong adaptive capability in fault environments, making it suitable for tasks that demand quick adaptation with limited sample data. These findings highlight WINFlowNets' potential for deployment in dynamic and malfunction-prone robotic systems, where traditional pre-training or sample inefficient data collection may be impractical.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 38 references that are in the map. First posted on arXiv 18 Mar 2026.

Builds on

31 of 38 references.

References · 31

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
  3. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  4. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  5. 2022Biological Sequence Design with GFlowNetscited by 174
  6. 2022GFlowNets and variational inferencecited by 106
  7. 2023A theory of continuous generative flow networkscited by 101
  8. 2023Better Training of GFlowNets with Local Credit and Incomplete Trajectoriescited by 85
  9. 2023Towards Understanding and Improving GFlowNet Trainingcited by 75
  10. 2023Robust Scheduling with GFlowNetscited by 69
  11. 2022Generative Augmented Flow Networkscited by 50
  12. 2023Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Networkcited by 50
19 more
  1. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  2. 2023Stochastic Generative Flow Networkscited by 32
  3. 2023CFlowNets: Continuous Control with Generative Flow Networkscited by 19
  4. 2024Embodied AI with Two Arms: Zero-shot Learning, Safety and Modularitycited by 19
  5. 2020Understanding and Mitigating the Limitations of Prioritized Experience Replaycited by 17
  6. 2018Accuracy-based Curriculum Learning in Deep Reinforcement Learningcited by 15
  7. 2023A Theory of Non-Acyclic Generative Flow Networkscited by 12
  8. 2023Provably Safe Reinforcement Learning with Step-wise Violation Constraintscited by 11
  9. 2024Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectoriescited by 9
  10. 2021MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerancecited by 8
  11. 2023Adapt On-the-Go: Behavior Modulation for Single-Life Robot Deploymentcited by 8
  12. 2023Expected flow networks in stochastic environments and two-player zero-sum gamescited by 7
  13. 2019Concurrent Meta Reinforcement Learningcited by 5
  14. 2020Fault-Aware Robust Control via Adversarial Reinforcement Learningcited by 5
  15. 2024GFlowNet Training by Policy Gradientscited by 5
  16. 2024Streaming Bayes GFlowNetscited by 4
  17. 2024Multi-Agent Continuous Control with Generative Flow Networkscited by 3
  18. 2020Complementary Meta-Reinforcement Learning for Fault-Adaptive Controlcited by 1
  19. 2025A Study of the Efficacy of Generative Flow Networks for Robotics and Machine Fault-Adaptationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets
  2. 2024Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
  3. 2025SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
  4. 2024Random Policy Evaluation Uncovers Policies of Generative Flow Networks
  5. 2025A Theory of Multi-Agent Generative Flow Networks
  6. 2025ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
  7. 2026GFlowRL: Scaling Distribution-Matching RL to Large Language Models
  8. 2024Improving GFlowNets with Monte Carlo Tree Search