mlsanityData to 14 Oct 2026

Hyperfastrl: Hypernetwork-based reinforcement learning for unified control of parametric chaotic PDEs

arXiv 2604.06497 ↗First posted 7 Apr 2026cs.CE cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

Spatiotemporal chaos in fluid systems exhibits severe parametric sensitivity, rendering classical adjoint-based optimal control intractable because each operating regime requires recomputing the control law. We address this bottleneck with hyperFastRL, a parameter-conditioned reinforcement learning framework that leverages Hypernetworks to shift from tuning isolated controllers per-regime to learning a unified parametric control manifold. By mapping a physical forcing parameter μ directly to the weights of a spatial feedback policy, the architecture cleanly decouples parametric adaptation from spatial boundary stabilization. To overcome the extreme variance inherent to chaotic reward landscapes, we deploy a pessimistic distributional value estimation over a massively parallel environment ensemble. We evaluate three Hypernetwork functional forms, ranging from residual MLPs to periodic Fourier and Kolmogorov-Arnold (KAN) representations, on the Kuramoto-Sivashinsky equation under varying spatial forcing. All forms achieve robust stabilization. KAN yields the most consistent energy-cascade suppression and tracking across unseen parametrizations, while Fourier networks exhibit worse extrapolation variability. Furthermore, leveraging high-throughput parallelization allows us to intentionally trade a fraction of peak asymptotic reward for a 37% reduction in training wall-clock time, identifying an optimal operating regime for practical deployment in complex, parameter-varying chaotic PDEs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 41 of its 89 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

41 of 89 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning13 Nov

Other references · 40

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  10. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  11. 2018On the Spectral Bias of Neural Networkscited by 1,341
  12. 2016HyperNetworkscited by 1,027
28 more
  1. 2019Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reductioncited by 840
  2. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  3. 2019Behavior Regularized Offline Reinforcement Learningcited by 662
  4. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  5. 2017Solving high-dimensional partial differential equations using deep learningcited by 556
  6. 2017Distributional Reinforcement Learning with Quantile Regressioncited by 474
  7. 2017Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equationscited by 191
  8. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 165
  9. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 66
  10. 2024Quantile Regression for Distributional Reward Models in RLHFcited by 60
  11. 2025FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Controlcited by 44
  12. 2021Recomposing the Reinforcement Learning Building Blocks with Hypernetworkscited by 35
  13. 2021Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equationscited by 30
  14. 2019Control of chaotic systems by Deep Reinforcement Learningcited by 29
  15. 2023Effective control of two-dimensional Rayleigh--B'enard convection: invariant multi-agent reinforcement learning is all you needcited by 27
  16. 2020Statistically Efficient Off-Policy Policy Gradientscited by 25
  17. 2023Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learningcited by 24
  18. 2021Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Controlcited by 23
  19. 2022Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learningcited by 17
  20. 2024Deep Learning Alternatives of the Kolmogorov Superposition Theoremcited by 12
  21. 2021Symmetry reduction for deep reinforcement learning active control of chaotic spatiotemporal dynamicscited by 11
  22. 2023Reconstruction, forecasting, and stability of chaotic dynamics from partial datacited by 8
  23. 2022Deep Reinforcement Learning for Computational Fluid Dynamics on HPC Systemscited by 7
  24. 2023Learning a model is paramount for sample efficiency in reinforcement learning control of PDEscited by 6
  25. 2019Restoring Chaos Using Deep Reinforcement Learningcited by 5
  26. 2024OMPO: A Unified Framework for RL under Policy and Dynamics Shiftscited by 5
  27. 2025Sample-Efficient Reinforcement Learning of Koopman eNMPCcited by 2
  28. 2019Model-free Control of Chaos with Continuous Deep Q-learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HypEMBER: Hypernetwork-based Ensemble for Robust Policy Learning of Parametrized Dynamical Systems
  2. 2025HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems
  3. 2025Improving the Robustness of Control of Chaotic Convective Flows with Domain-Informed Reinforcement Learning
  4. 2025HypeMARL: Multi-Agent Reinforcement Learning For High-Dimensional, Parametric, and Distributed Systems
  5. 2025Data-Assimilated Model-Based Reinforcement Learning for Partially Observed Chaotic Flows
  6. 2026On Distributional Reinforcement Learning in Chaotic Dynamical Systems
  7. 2025Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay
  8. 2024Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems