Learning minimum-time navigation policies in two-dimensional flows with a genetic algorithm
Abstract
We study minimum-time navigation between two points in a known two-dimensional fluid flow for a vessel with fixed-magnitude slip velocity and controllable direction. The navigation policy is parameterized by a neural network and optimized using a genetic algorithm that evolves an ensemble of candidate strategies through Darwinian selection and parameter mutation, without crossover. The method recovers analytical and numerical optimal-control solutions in several benchmark cases, including two-dimensional turbulence, and outperforms Q-learning and one-step actor-critic method. We further show that the learned navigation strategies are robust to variations in the starting position and to unresolved small-scale turbulent fluctuations, provided that the characteristic velocity of these fluctuations remains small compared to the vessel's slip velocity. The proposed approach provides a compact representation of the navigation policy, is readily parallelizable, and eliminates the need for reward shaping, offering an efficient alternative to existing analytical and numerical methods for computing minimum-time trajectories in complex flows.
Related
- Autonomous Droplet Navigation via Model-Based Reinforcement Learning
- Learning and interpreting policies for simultaneous entanglement requests in quantum networks
- Quantum algorithm for high-dimensional nonlinear stochastic differential equations based on Carleman linearization
- Comparison of spectral performance of three dual-energy CT scanners equipped with a deep-learning image reconstruction algorithm and one photon counting CT scanner: A phantom study
- Application a quantum machine learning algorithm to the applied problem of modeling the thermal regime of a servers
BibTeX
@misc{parfenyev2026learning,
title = {{Learning minimum-time navigation policies in two-dimensional flows with a genetic algorithm}},
author = {Vladimir Parfenyev},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.12177},
eprint = {2610.12177},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.12177},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning minimum-time navigation policies in two-dimensional flows with a genetic algorithm
AU - Vladimir Parfenyev
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.12177
UR - https://arxiv.org/abs/2610.12177
AB - We study minimum-time navigation between two points in a known two-dimensional fluid flow for a vessel with fixed-magnitude slip velocity and controllable direction. The navigation policy is parameterized by a neural network and optimized using a genetic algorithm that evolves an ensemble of candidate strategies through Darwinian selection and parameter mutation, without crossover. The method recovers analytical and numerical optimal-control solutions in several benchmark cases, including two-dimensional turbulence, and outperforms Q-learning and one-step actor-critic method. We further show that the learned navigation strategies are robust to variations in the starting position and to unresolved small-scale turbulent fluctuations, provided that the characteristic velocity of these fluctuations remains small compared to the vessel's slip velocity. The proposed approach provides a compact representation of the navigation policy, is readily parallelizable, and eliminates the need for reward shaping, offering an efficient alternative to existing analytical and numerical methods for computing minimum-time trajectories in complex flows.
ER -