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

Collective behavior, and swarm formation in particular, has been studied fromseveral perspectives within a large variety of fields, ranging from biology tophysics. In this work, we apply Projective Simulation to model each individualas an artificial learning agent that interacts with its neighbors andsurroundings in order to make decisions and learn from them. Within areinforcement learning framework, we discuss one-dimensional learning scenarioswhere agents need to get to food resources to be rewarded. We observe howdifferent types of collective motion emerge depending on the distance theagents need to travel to reach the resources. For instance, strongly alignedswarms emerge when the food source is placed far away from the region whereagents are situated initially. In addition, we study the properties of theindividual trajectories that occur within the different types of emergentcollective dynamics. Agents trained to find distant resources exhibitindividual trajectories with L\'evy-like characteristics as a consequence ofthe collective motion, whereas agents trained to reach nearby resources presentBrownian-like trajectories.

Development of swarm behavior in artificial learning agents that adapt to different foraging environments