Subjective functions
This addresses a foundational issue in AI and cognitive science for researchers and developers, but it appears incremental as it builds on existing ideas without presenting new empirical results.
The paper tackles the problem of how agents, particularly artificial systems, can autonomously generate objective functions, proposing the concept of a subjective function as a higher-order objective defined endogenously, with expected prediction error as a concrete example.
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.