English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We apply a reinforcement learning algorithm to show how smart particles canlearn approximately optimal strategies to navigate in complex flows. In thispaper we consider microswimmers in a paradigmatic three-dimensional case givenby a stationary superposition of two Arnold-Beltrami-Childress flows withchaotic advection along streamlines. In such a flow, we study the evolution ofpoint-like particles which can decide in which direction to swim, while keepingthe velocity amplitude constant. We show that it is sufficient to endow theswimmers with a very restricted set of actions (six fixed swimming directionsin our case) to have enough freedom to find efficient strategies to move upwardand escape local fluid traps. The key ingredient is thelearning-from-experience structure of the algorithm, which assigns positive ornegative rewards depending on whether the taken action is, or is not,profitable for the predetermined goal in the long term horizon. This is anotherexample supporting the efficiency of the reinforcement learning approach tolearn how to accomplish difficult tasks in complex fluid environments.

Finding Efficient Swimming Strategies in a Three Dimensional Chaotic Flow by Reinforcement Learning