# Flow Navigation by Smart Microswimmers via Reinforcement Learning

## TL;DR

This paper demonstrates how reinforcement learning enables smart microswimmers to adaptively navigate complex fluid flows, effectively reaching high altitudes despite flow-induced traps, with potential applications in engineering autonomous micro-robots.

## Contribution

It introduces a reinforcement learning framework for microswimmers to learn complex navigation strategies in fluid flows, surpassing traditional control methods.

## Key findings

- Swimmers learn nearly optimal navigation strategies through experience.
- Reinforcement learning enables effective escape from flow traps.
- Strategies learned are highly nontrivial and not easily guessed.

## Abstract

Smart active particles can acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. Their goal is to learn the best way to navigate by exploiting the underlying flow whenever possible. As an example, we focus our attention on smart gravitactic swimmers. These are active particles whose task is to reach the highest altitude within some time horizon, given the constraints enforced by fluid mechanics. By means of numerical experiments, we show that swimmers indeed learn nearly optimal strategies just by experience. A reinforcement learning algorithm allows particles to learn effective strategies even in difficult situations when, in the absence of control, they would end up being trapped by flow structures. These strategies are highly nontrivial and cannot be easily guessed in advance. This Letter illustrates the potential of reinforcement learning algorithms to model adaptive behavior in complex flows and paves the way towards the engineering of smart microswimmers that solve difficult navigation problems.