학술논문
Learning agents that acquire representations of social groups.
Document Type
Article
Author
Source
Subject
*REINFORCEMENT learning
*COLLECTIVE representation
*SOCIAL groups
*
*
Language
ISSN
0140-525X
Abstract
Humans are learning agents that acquire social group representations from experience. Here, we discuss how to construct artificial agents capable of this feat. One approach, based on deep reinforcement learning, allows the necessary representations to self-organize. This minimizes the need for hand-engineering, improving robustness and scalability. It also enables "virtual neuroscience" research on the learned representations. [ABSTRACT FROM AUTHOR]