Inferring Affective Consciousness in an Artificial Agent: A Case Study

📅 2026-09-03
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
研究通过构建一个能展示享乐地点偏好的人工代理,探讨其在确定性机制下如何模拟体验不确定性及内在需求,以此探索意识和自由意志的物理基础。
📝 Abstract
Creatures that display 'hedonic place preference behaviour' are thought by many scientists to experience feelings, on the assumption that their attraction to pleasure-producing substances which lack nutritional value (e.g. cocaine, morphine) cannot easily be attributed to unconscious instinctual behaviour. In this paper, we discuss how a simple artificial agent that instantiates attributes of an affective system engaging in felt uncertainty about its intrinsic needs in relation to environmental resources can similarly display hedonic place preference behaviour -- through an apparently subjective form of information processing -- while simultaneously being entirely deter-ministic. We outline some implications of this artificially engineered behaviour for our understanding of the physical basis of consciousness and the experience of free will.
Problem

Research questions and friction points this paper is trying to address.

affective consciousness
artificial agent
hedonic place preference behaviour
Innovation

Methods, ideas, or system contributions that make the work stand out.

affective consciousness
artificial agent
hedonic place preference
deterministic mechanism
subjective information processing
💼 Related Jobs
No related jobs found.
Mark Solms
Mark Solms
Professor of Neuropsychology, University of Cape Town
NeuropsychologyPsychoanalysis
S
St John Grimbly
Neuroscience Institute, University of Cape Town, South Africa; Dept. of Mathematics & Applied Mathematics, University of Cape Town, South Africa
Bruce Bassett
Bruce Bassett
WITS/UCT
AIBayesian methodsCosmology
E
Evert Boonstra
Neuroscience Institute, University of Cape Town, South Africa; Dept. of Psychology, University of Cape Town, South Africa
R
Rowan Hodson
Laureate Institute for Brain Research, University of Tulsa, OK, USA
N
Nicolas Kuske
Neuroscience Institute, University of Cape Town, South Africa; Dept. of Mathematics & Applied Mathematics, University of Cape Town, South Africa
K
Kival Mahadew
Neuroscience Institute, University of Cape Town, South Africa; Dept. of Mathematics & Applied Mathematics, University of Cape Town, South Africa
Benjamin Rosman
Benjamin Rosman
Professor at the University of the Witwatersrand, South Africa
RoboticsArtificial IntelligenceMachine LearningDecision MakingReinforcement Learning
C
Charel van Hoof
Dept. of Cognitive Robotics, Delft University of Technology, Delft, Netherlands
Jonathan Shock
Jonathan Shock
Associate Professor in Mathematics and Applied Mathematics, University of Cape Town
Reinforcement learningString theorycognitive and computational neurosciencemedical data analysismachine learning