mlsanityData to 14 Oct 2026

Control of Rayleigh-B'enard Convection: Effectiveness of Reinforcement Learning in the Turbulent Regime

arXiv 2504.12000 ↗First posted 16 Apr 2025physics.flu-dyn cs.LGcited by 2

On the map: Deep reinforcement learning methods → RL with diffusion and flow models

Abstract (arXiv)

Data-driven flow control has significant potential for industry, energy systems, and climate science. In this work, we study the effectiveness of Reinforcement Learning (RL) for reducing convective heat transfer in the 2D Rayleigh-B'enard Convection (RBC) system under increasing turbulence. We investigate the generalizability of control across varying initial conditions and turbulence levels and introduce a reward shaping technique to accelerate the training. RL agents trained via single-agent Proximal Policy Optimization (PPO) are compared to linear proportional derivative (PD) controllers from classical control theory. The RL agents reduced convection, measured by the Nusselt Number, by up to 33% in moderately turbulent systems and 10% in highly turbulent settings, clearly outperforming PD control in all settings. The agents showed strong generalization performance across different initial conditions and to a significant extent, generalized to higher degrees of turbulence. The reward shaping improved sample efficiency and consistently stabilized the Nusselt Number to higher turbulence levels.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 16 references that are in the map. First posted on arXiv 16 Apr 2025.

Builds on

8 of 16 references.

References · 8

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2019A review on Deep Reinforcement Learning for Fluid Mechanicscited by 66
  3. 2023Effective control of two-dimensional Rayleigh--B'enard convection: invariant multi-agent reinforcement learning is all you needcited by 27
  4. 2020Controlling Rayleigh-B'enard convection via Reinforcement Learningcited by 25
  5. 2024Multi-agent reinforcement learning for the control of three-dimensional Rayleigh-B'enard convectioncited by 8
  6. 2024Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and qualitycited by 5
  7. 2025Solving Turbulent Rayleigh-B'enard Convection using Fourier Neural Operatorscited by 5
  8. 2024Koopman-Based Surrogate Modelling of Turbulent Rayleigh-B'enard Convectioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Controlcited by 2
  2. 2026Koopman-based surrogate modeling for reinforcement-learning-control of Rayleigh-Benard convectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving the Robustness of Control of Chaotic Convective Flows with Domain-Informed Reinforcement Learning
  2. 2026Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
  3. 2025Physics-informed Neural-operator Predictive Control for Drag Reduction in Turbulent Flows
  4. 2025Data-Assimilated Model-Based Reinforcement Learning for Partially Observed Chaotic Flows
  5. 2026Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
  6. 2025The HydroGym Reinforcement Learning Platform for Fluid Dynamics
  7. 2026Generalizing HVAC Control With Domain Randomized Reinforcement Learning
  8. 2026Physics-guided surrogate learning enables zero-shot control of turbulent wings