Design and evaluation of a global workspace agent embodied in a realistic multimodal environment.
Frontiers in Computational Neuroscience January 1, 2024 Rousslan Fernand Julien Dossa, Kai Arulkumaran, Arthur Juliani et al.
An embodied agent with a structure based on global workspace theory, trained on realistic audiovisual inputs to navigate 3D environments, performs better and more robustly at smaller working memory sizes compared to a standard recurrent architecture. Task complexity and regularization are essential for feature learning and the development of meaningful attentional patterns within the workspace.