Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 29 min ago
PreprintCC BY 4.0arXiv

Inferring Affective Consciousness in an Artificial Agent: A Case Study

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.

Versions

Related

  1. CTM-AI: Evolving Multi-Agent Intelligence Inspired by a Model of Consciousness
    Haofei Yu, Yining Zhao, Lenore Blum +2
    arXivPreprintCC BY 4.0Full textNeurosciencearXiv
  2. From Biological Precursors to Artificial Cognition: Consciousness, Embodiment, and the MEM Architecture
    Janusz A. Starzyk, Wiesław L. Galus
    arXivPreprintCC BY-NC-ND 4.0Full textNeurosciencearXiv
  3. Inferring the age of a fixed beneficial allele.
    Louise Ormond, Matthieu Foll, Gregory B Ewing +2
    Molecular EcologyPeer-reviewedLicence not stated24 citedGenetics & genomicsHAL
  4. WFABC: a Wright-Fisher ABC-based approach for inferring effective population sizes and selection coefficients from time-sampled data
    Matthieu Foll, Hyunjin Shim, Jeffrey D Jensen
    Molecular Ecology ResourcesPeer-reviewedLicence not statedFull text123 citedGenetics & genomicsHAL
  5. TraSPIN: inferring transporter specificity through language model-guided graph learning
    Tong Pan, Jie Liu, Jing Xu +7
    Genome BiologyPeer-reviewedCC BY-NC-ND 4.0Molecular biology & gene regulationGenetics & genomicsCrossref
BibTeX
@misc{solms2026inferring,
  title = {{Inferring Affective Consciousness in an Artificial Agent: A Case Study}},
  author = {Mark Solms and St John Grimbly and Bruce Bassett and Evert Boonstra and Rowan Hodson and Nicolas Kuske and Kival Mahadew and Benjamin Rosman and Charel van Hoof and Jonathan Shock},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.03883},
  eprint = {2609.03883},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.03883},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Inferring Affective Consciousness in an Artificial Agent: A Case Study
AU  - Mark Solms
AU  - St John Grimbly
AU  - Bruce Bassett
AU  - Evert Boonstra
AU  - Rowan Hodson
AU  - Nicolas Kuske
AU  - Kival Mahadew
AU  - Benjamin Rosman
AU  - Charel van Hoof
AU  - Jonathan Shock
PY  - 2026
DA  - 2026/09/03
PB  - arXiv
DO  - 10.48550/arxiv.2609.03883
UR  - https://arxiv.org/abs/2609.03883
AB  - 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.
ER  -