
TL;DR
This paper explores the concept of subjective functions, higher-order goal functions endogenous to agents, using expected prediction error as a key example, linking psychology, neuroscience, and machine learning.
Contribution
It introduces the idea of subjective functions as endogenous goal generators and analyzes expected prediction error as a concrete example.
Findings
Expected prediction error can serve as a subjective function.
Subjective functions are connected to psychological and neuroscientific theories.
This framework offers a new perspective on goal selection in artificial agents.
Abstract
Where do objective functions come from? How do we select what goals to pursue? Human intelligence is adept at synthesizing new objective functions on the fly. How does this work, and can we endow artificial systems with the same ability? This paper proposes an approach to answering these questions, starting with 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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
