Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction

• URL: http://arxiv.org/abs/2606.31025v1
• Date: Tue, 30 Jun 2026 01:46:48 GMT
• Title: Offline Reinforcement Learning for Fluid Controls: Data-based Multi-observational Policy Extraction
• Abstract summary: We develop a sensor position-conditioned architecture that enables a single policy network to adapt seamlessly to multiple sensor arrangements.<n>We demonstrate the framework on two representative problems, mitigating chaoticity in the Kuramoto-Sivashinsky equation and flow control over airfoils governed by the Navier-Stokes equation.
• Score: 9.85263518243188
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Active flow control is a fundamental application in engineering. Recent advances in deep reinforcement learning have made progress in this field. However, the classical online RL approaches require extensive real-time interactions with the high fidelity environment, while each sensor configuration change necessitates whole policy retraining. All these factors result in prohibitive computational costs for real-world applications. In this work, we propose a novel offline RL framework that addresses both challenges through data-driven policy extraction. We develop a sensor position-conditioned architecture that enables a single policy network to adapt seamlessly to multiple sensor arrangements. The position-conditioned approach incorporated spatial relationship modeling through Point Attention layers to ensure the generalizability to varying sensor placements. We demonstrate the framework on two representative problems, mitigating chaoticity in the Kuramoto-Sivashinsky equation and flow control over airfoils governed by the Navier-Stokes equation. The result demonstrates that the policy extraction from the dataset provides unprecedented flexibility for sensor placement optimization. This approach represents a significant step towards adaptive, intelligent flow control systems.

Related papers

• Learning to Optimize UAV Path Planning for Data Sensing in Wireless Sensor Networks [15.490344146407798]
  We propose a novel learning-assisted planning framework, termed Landscape-Aware Meta Differential Evolution (LAMDE)<n>LAMDE achieves state-of-the-art performance on the tested complex UAV path planning tasks in WSN data collection scenarios.
  arXiv  Detail & Related papers  (2026-09-15T04:51:47Z)
• Bypassing the CSI Bottleneck: MARL-Driven Spatial Control for Reflector Arrays [8.046649921554472]
  This paper presents a fully autonomous Multi-Agent Reinforcement Learning (MARL) framework to control mechanically adjustable metallic reflector arrays.<n>High-fidelity ray-tracing simulations in dynamic non-line-of-sight (NLOS) environments demonstrate that this multi-agent approach rapidly adapts to user mobility.<n>These results validate the efficacy of MARL-driven spatial abstractions as a scalable, highly practical pathway toward AI-empowered wireless networks.
  arXiv  Detail & Related papers  (2026-04-06T20:47:50Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control [61.155940786140455]
  Reinforcement learning (RL) has shown promising results in active flow control (AFC)<n>Current AFC benchmarks rely on external computational fluid dynamics (CFD) solvers, are not fully differentiable, and provide limited 3D and multi-agent support.<n>We introduce FluidGym, the first standalone, fully differentiable benchmark suite for RL in AFC.
  arXiv  Detail & Related papers  (2026-01-21T14:13:44Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• Deep Learning Optimization of Two-State Pinching Antennas Systems [48.70043547158868]
  Pinching antennas (PAs) can dynamically control electromagnetic wave propagation through binary activation states.<n>In this work, we investigate the problem of optimally selecting a subset of fixed-position PAs to activate in a waveguide, when the aim is to maximize the communication rate at a user terminal.
  arXiv  Detail & Related papers  (2025-07-08T17:55:54Z)
• Efficient Unsupervised Domain Adaptation Regression for Spatial-Temporal Sensor Fusion [6.963971634605796]
  Low-cost, distributed sensor networks in environmental and biomedical domains have enabled continuous, large-scale health monitoring.<n>These systems often face challenges related to degraded data quality caused by sensor drift, noise, and insufficient calibration.<n>Traditional machine learning methods for sensor fusion and calibration rely on extensive feature engineering.<n>We propose a novel unsupervised domain adaptation (UDA) method tailored for regression tasks.
  arXiv  Detail & Related papers  (2024-11-11T12:20:57Z)
• Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality [0.7421845364041001]
  This study advances deep-reinforcement-learning (DRL) methods for flow control. We focus on integrating group-invariant networks and positional encoding into DRL architectures. The proposed methods are verified using a case study of Rayleigh-B'enard convection.
  arXiv  Detail & Related papers  (2024-07-25T07:24:41Z)
• Design Optimization of NOMA Aided Multi-STAR-RIS for Indoor Environments: A Convex Approximation Imitated Reinforcement Learning Approach [51.63921041249406]
  Non-orthogonal multiple access (NOMA) enables multiple users to share the same frequency band, and simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) deploying STAR-RIS indoors presents challenges in interference mitigation, power consumption, and real-time configuration. A novel network architecture utilizing multiple access points (APs), STAR-RISs, and NOMA is proposed for indoor communication.
  arXiv  Detail & Related papers  (2024-06-19T07:17:04Z)
• Sim-Anchored Learning for On-the-Fly Adaptation [45.123633153460034]
  Fine-tuning simulation-trained RL agents with real-world data often degrades crucial behaviors due to limited or skewed data distributions.<n>We propose framing live-adaptation as a multi-objective optimization problem, where policy objectives must be satisfied both in simulation and reality.
  arXiv  Detail & Related papers  (2023-01-17T16:16:53Z)
• Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows [58.762959061522736]
  offline reinforcement learning aims to train a policy on a pre-recorded and fixed dataset without any additional environment interactions. We build upon recent works on learning policies in latent action spaces and use a special form of Normalizing Flows for constructing a generative model. We evaluate our method on various locomotion and navigation tasks, demonstrating that our approach outperforms recently proposed algorithms.
  arXiv  Detail & Related papers  (2022-11-20T21:57:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.