Tag
This paper advocates for incorporating enactive approaches to perception and cognition into AI, highlighting four key concepts: experience, action-perception inseparability, autonomy, and embodiment. It finds resonance with reinforcement learning but suggests broader integration of enactive ideas.
This paper proposes a minimal architecture for body-grounded perspective formation in artificial agents, extending prior work with an interoceptive viability signal and conative alignment mechanism to operationalize machine subjectivity from a phenomenological perspective.