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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Navigation is a complex skill with a long history of research in animals andhumans. In this work, we simulate the Morris Water Maze in 2D to train deepreinforcement learning agents. We perform automatic classification ofnavigation strategies, analyze the distribution of strategies used byartificial agents, and compare them with experimental data to show similarlearning dynamics as those seen in humans and rodents. We developenvironment-specific auxiliary tasks and examine factors affecting theirusefulness. We suggest that the most beneficial tasks are potentially morebiologically feasible for real agents to use. Lastly, we explore thedevelopment of internal representations in the activations of artificial agentneural networks. These representations resemble place cells and head-directioncells found in mouse brains, and their presence has correlation to thenavigation strategies that artificial agents employ.

Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning