Results 141 to 150 of about 119,392 (258)

Emergent Braitenberg-style Behaviours for Navigating the ViZDoom `My Way Home' Labyrinth [PDF]

open access: yesarXiv
The navigation of complex labyrinths with tens of rooms under visual partially observable state is typically addressed using recurrent deep reinforcement learning architectures. In this work, we show that navigation can be achieved through the emergent evolution of a simple Braitentberg-style heuristic that structures the interaction between agent and ...
arxiv  

Sequestra of Labyrinth [PDF]

open access: yesProceedings of the Royal Society of Medicine, 1925
openaire   +3 more sources

Home - About - Disclaimer - Privacy