mlsanityData to 14 Oct 2026

A Two-Stage, Model-Based Reinforcement Learning Approach for Active Flow Control of Bluff Body Wakes

arXiv 2609.08436 ↗First posted 8 Sep 2026eess.SY cs.SYcited by 0

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

Abstract (arXiv)

This paper develops a data-driven, output-feedback approach to the infinite-horizon optimal control of high-dimensional nonlinear systems with unknown and unstable equilibria, using sparse partial observations. The approach builds on the transfer-plus-regulation decomposition of the infinite-horizon problem: a finite-horizon nonlinear transfer drives the system into a region where the dynamics are well-approximated by a linear model about the unknown operating point, and an infinite-horizon linear regulator identified within that region completes stabilization. We extend this framework to the partially observed setting by combining an ARMA-based information-state construction with a two-stage control architecture: an iterative linear quadratic regulator (iLQR) approach on the information state drives the system to the equilibrium neighborhood, discovered implicitly without prior knowledge of the target, and a locally identified time-invariant ARMA model provides the infinite-horizon regulator for asymptotic stabilization. The method requires no adjoint solver, reduced-order model, or full-state access. We validate the approach on high-fidelity Navier-Stokes simulations of the cylinder wake at Re=100 using only eight surface pressure sensors, an order of magnitude fewer than recent model-based RL methods. The controller achieves complete suppression of vortex-shedding-induced lift oscillations and a 44% reduction in total drag relative to the uncontrolled baseline.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL with diffusion and flow models, one of 15 directions in Deep reinforcement learning methods. Builds on 2 of its 18 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

2 of 18 references.

References · 2

  1. 2023An Optimal Solution to Infinite Horizon Nonlinear Control Problemscited by 1
  2. 2024An Optimal Solution to Infinite Horizon Nonholonomic and Discounted Nonlinear Control Problemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
  2. 2026Heuristic Learning for Active Flow Control Using Coding Agents
  3. 2025Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
  4. 2025Invariant Control Strategies for Active Flow Control using Graph Neural Networks
  5. 2024Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows
  6. 2025Data-Assimilated Model-Based Reinforcement Learning for Partially Observed Chaotic Flows
  7. 2025Domain Adaptation of Drag Reduction Policy to Partial Measurements
  8. 2026Enhancing sample efficiency in reinforcement-learning-based flow control: replacing the critic with an adaptive reduced-order model