How Intrinsic Motivation Underlies Embodied Open-Ended Behavior

URL

Notes

Abstract

some behaviors appear to be reward independent ()

intrinsic motivation has emerged as a potentially major driver of behavior ()

behavior as being organized hierarchically: objective–intrinsic reward, or motivation–drives, goals and extrinsic reward ()

main formalizations of intrinsic motivation, including empowerment, the free energy principle, information-gain maximization, and the maximum occupancy principle ()

Bounded cognition and embodiment impose constraints and boundary conditions for the intrinsic motivation objective ()

theories of intrinsic motivation promise to become successful generative models of open-ended, embodied behavior ()

Extrinsic rewards are a means for achieving the maximization of the intrinsic motivation objective ()

Extrinsic Reward Maximization vs. Intrinsic Motivation

The result for each of your extrinsic reward designs would be an inflexible behavior that becomes more deterministic as learning progresses (3)

optimal behavioral policy* (see Glossary) becomes a one-to-one mapping between states and actions in a Markov Decision Process (3)

Collapse into repetitive behavior is rarely observed, and rather it is typically considered a signature of mental or psychological disorders, such as eating disorders (3)

extrinsic rewards are sought temporarily, but after enough consumption of them, what drives behavior is a signal of a different nature, e.g., an insatiable intrinsic motivation for exploration (3)

natural behavior by providing it with open-endedness, constrained only by bounded cognition* and embodiment* (3)