In the field of artificial intelligence, where do objective functions come from? How do we select the goals to pursue? Human intelligence excels at dynamically synthesizing new objective functions. This paper proposes an approach to answer these questions by introducing the concept of a subjective function, a higher-order objective function that is endogenous to the agent (i.e., defined with respect to the agent's features rather than an external task).
Expected prediction error is studied as a concrete example of a subjective function. This proposal has many connections to ideas in psychology, neuroscience, and machine learning.
Blogger's Review: This exploration of subjective functions not only enriches the theoretical framework of goal setting but also provides a new perspective for adaptive learning in AI. The integration of psychology and machine learning is a promising avenue for further research.