Timescale Separation Enables Deep Reinforcement Learning Control of Rotating Detonation Engine Mode Transitions

arXiv:2604.14398 · physics.flu-dyn, cs.LG · Submitted 2026-04-15 · Read on arXiv

physics.flu-dyn, cs.LG

Submitted: 2026-04-15

Updated: 2026-10-02

Code: https://github.com/KristianHolme/RDE.jl

Terminology

• Deep Reinforcement Learning — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Deep Reinforcement Learning (DRL) — 1× in this paper · explained in 2 episodes

Sources

• Proximal Policy Optimization Algorithms

Related papers

• Fluids You Can Trust: Property-Preserving Operator Learning for Incompressible Flows
• Physics Foundation Models for Efficient Control of Fluid Flows
• Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields
• Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
• Reward hacking in physical reinforcement learning revealed by turbulent drag reduction
• Diffraction of walking drops by a standing Faraday wave