A goal-centric outlook on learning

Published on September 10, 2023

In the realm of learning and decision-making, goals are like the guiding stars that shape our paths. Just as a compass points the way in uncharted territory, setting a goal influences how we perceive information, choose actions, and interpret outcomes. Computational theories often overlook the significant role of goals, but empirical evidence reveals their profound impact on the learning process. To truly grasp the intricacies of learning, we need to delve into the study of goal selection. Drawing from existing research, we can uncover the underlying principles of goal value attribution and exploration strategies. By adopting a goal-centric perspective, we can gain a more comprehensive understanding of learning in both living organisms and artificial intelligence systems.

Goals play a central role in human cognition. However, computational theories of learning and decision-making often take goals as given. Here, we review key empirical findings showing that goals shape the representations of inputs, responses, and outcomes, such that setting a goal crucially influences the central aspects of any learning process: states, actions, and rewards. We thus argue that studying goal selection is essential to advance our understanding of learning. By following existing literature in framing goal selection within a hierarchy of decision-making problems, we synthesize important findings on the principles underlying goal value attribution and exploration strategies. Ultimately, we propose that a goal-centric perspective will help develop more complete accounts of learning in both biological and artificial agents.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>