Subjective functions
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 77 references that are in the map. First posted on arXiv 17 Dec 2025.
Builds on
14 of 77 references.
References · 14
- 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
- 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,173
- 2018Meta-Gradient Reinforcement Learningcited by 156
- 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 145
- 2018On Learning Intrinsic Rewards for Policy Gradient Methodscited by 100
- 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 83
- 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
- 2019Improving Generalization in Meta Reinforcement Learning using Learned Objectivescited by 68
- 2019Meta-Learning via Learned Losscited by 60
- 2020Meta-Gradient Reinforcement Learning with an Objective Discovered Onlinecited by 52
- 2019What Can Learned Intrinsic Rewards Capture?cited by 36
- 2020Temporal Difference Uncertainties as a Signal for Explorationcited by 15
Built on by
Not cited yet.