How Intrinsic Motivation Underlies Embodied Open-Ended Behavior
Rub\'en Moreno-Bote, Ralf Haefner, Jordi Galiano-Landeira, Tianming Yang, Pedro Maldonado

TL;DR
This paper explores how intrinsic motivation, independent of extrinsic rewards, can drive complex, open-ended embodied behaviors, supported by a hierarchical framework and various formal theories.
Contribution
It introduces a hierarchical framework linking intrinsic motivation to behavior and reviews formal models like empowerment and free energy, highlighting their role in generating complex behaviors.
Findings
Intrinsic motivation can organize behavior hierarchically.
Formal theories promote entropic action paths.
Intrinsic motivation models generate complex, task-agnostic behaviors.
Abstract
Although most theories posit that natural behavior can be explained as maximizing some form of extrinsic reward, often called utility, some behaviors appear to be reward independent. For instance, spontaneous motor babbling in human newborns and curiosity in little kids and other animals seem to elude a simple explanation in terms of extrinsic reward maximization. Rooted in these observations, intrinsic motivation has emerged as a potentially major driver of behavior. However, only recently have several quantitative and foundational theories of intrinsic motivation been put forward. We first provide a general framework to understand behavior as being organized hierarchically: objective--intrinsic reward, or motivation--drives, goals and extrinsic reward. We next review the main formalizations of intrinsic motivation, including empowerment, the free energy principle, information-gain…
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.
Taxonomy
TopicsEmbodied and Extended Cognition · Child and Animal Learning Development · Action Observation and Synchronization
