Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Koh, Christopher, Pagnier, Laurent, Chertkov, Michael
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909381613846528
author Koh, Christopher
Pagnier, Laurent
Chertkov, Michael
author_facet Koh, Christopher
Pagnier, Laurent
Chertkov, Michael
contents Turbulent diffusion causes particles placed in proximity to separate. We investigate the required swimming efforts to maintain an active particle close to its passively advected counterpart. We explore optimally balancing these efforts by developing a novel physics-informed reinforcement learning strategy and comparing it with prescribed control and physics-agnostic reinforcement learning strategies. Our scheme, coined the actor-physicist, is an adaptation of the actor-critic algorithm in which the neural network parameterized critic is replaced with an analytically derived physical heuristic function, the physicist. We validate the proposed physics-informed reinforcement learning approach through extensive numerical experiments in both synthetic BK and more realistic Arnold-Beltrami-Childress flow environments, demonstrating its superiority in controlling particle dynamics when compared to standard reinforcement learning methods.
format Preprint
id arxiv_https___arxiv_org_abs_2406_10242
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence
Koh, Christopher
Pagnier, Laurent
Chertkov, Michael
Systems and Control
Machine Learning
Chaotic Dynamics
Fluid Dynamics
Turbulent diffusion causes particles placed in proximity to separate. We investigate the required swimming efforts to maintain an active particle close to its passively advected counterpart. We explore optimally balancing these efforts by developing a novel physics-informed reinforcement learning strategy and comparing it with prescribed control and physics-agnostic reinforcement learning strategies. Our scheme, coined the actor-physicist, is an adaptation of the actor-critic algorithm in which the neural network parameterized critic is replaced with an analytically derived physical heuristic function, the physicist. We validate the proposed physics-informed reinforcement learning approach through extensive numerical experiments in both synthetic BK and more realistic Arnold-Beltrami-Childress flow environments, demonstrating its superiority in controlling particle dynamics when compared to standard reinforcement learning methods.
title Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence
topic Systems and Control
Machine Learning
Chaotic Dynamics
Fluid Dynamics
url https://arxiv.org/abs/2406.10242