The Archimedean trap: Why traditional reinforcement learning will probably not yield AGI

Al-Dhalimy, H., and Geyer, C. J. 2016. Surreal Time and Ultratasks. The Review of Symbolic Logic 9(4):836–847.10.1017/S1755020316000289Search in Google Scholar

Alexander, S. A. 2019a. Intelligence via ultrafilters: structural properties of some intelligence comparators of deterministic Legg-Hutter agents. Journal of Artificial General Intelligence 10:24–45.10.2478/jagi-2019-0003Search in Google Scholar

Alexander, S. A. 2019b. Measuring the intelligence of an idealized mechanical knowing agent. In Cognition, Interdisciplinary Foundations, Models, and Applications (CIFMA).10.1007/978-3-030-57506-9_13Search in Google Scholar

Andréka, H.; Madarász, J. X.; Németi, I.; and Székely, G. 2012. A logic road from special relativity to general relativity. Synthese 186(3):633–649.10.1007/s11229-011-9914-8Search in Google Scholar

Archimedes. 1897. On the Sphere and Cylinder. In Heath, T., ed., The works of Archimedes. Cambridge University Press.Search in Google Scholar

Bair, J.; B laszczyk, P.; Ely, R.; Henry, V.; Kanovei, V.; Katz, K. U.; Katz, M. G.; Kutateladze, S. S.; McGaffey, T.; Schaps, D. M.; Sherry, D.; and Shnider, S. 2013. Is mathematical history written by the victors? Notices of the American Mathematical Society 60(7):886–904.Search in Google Scholar

Benci, V.; Horsten, L.; and Wenmackers, S. 2013. Non-Archimedean probability. Milan Journal of Mathematics 81(1):121–151.10.1007/s00032-012-0191-xSearch in Google Scholar

Blum, D., and Holling, H. 2017. Spearman’s law of diminishing returns. A meta-analysis. Intelligence 65:60–66.Search in Google Scholar

Chen, L. 2020. Infinitesimal gunk. Journal of Philosophical Logic 49:981–1004.10.1007/s10992-020-09544-xSearch in Google Scholar

Conway, J. H. 2000. On Numbers and Games. CRC Press, 2nd edition.10.1201/9781439864159Search in Google Scholar

Ehrlich, P. 2012. The absolute arithmetic continuum and the unification of all numbers great and small. Bulletin of Symbolic Logic 18:1–45.10.2178/bsl/1327328438Search in Google Scholar

Euclid. 2007. Book V: Theory of Proportion. In Casey, J., ed., First Six Books of the Elements of Euclid. Project Gutenburg.Search in Google Scholar

Hernández-Orallo, J. 2019. AI Generality and Spearman’s Law of Diminishing Returns. Journal of Artificial Intelligence Research 64:529–562.10.1613/jair.1.11388Search in Google Scholar

Hibbard, B. 2011. Measuring agent intelligence via hierarchies of environments. In International Conference on Artificial General Intelligence, 303–308. Springer.10.1007/978-3-642-22887-2_34Search in Google Scholar

Knuth, D. E. 1974. Surreal numbers: a mathematical novelette. Addison-Wesley.Search in Google Scholar

Legg, S., and Hutter, M. 2007. Universal intelligence: A definition of machine intelligence. Minds and machines 17(4):391–444.10.1007/s11023-007-9079-xSearch in Google Scholar

Livingston, S.; Garvey, J.; and Elhanany, I. 2008. On the broad implications of reinforcement learning based AGI. In International Conference on Artificial General Intelligence, 478–482.Search in Google Scholar

Maruyama, Y. 2020. Symbolic and Statistical Theories of Cognition: Towards Integrated Artificial Intelligence. In Cognition, Interdisciplinary Foundations, Models, and Applications (CIFMA).Search in Google Scholar

Mill, J. S. 2016. Utilitarianism. In Seven masterpieces of philosophy. Routledge. 337–383.10.4324/9781315508818-12Search in Google Scholar

Narens, L. 1974. Measurement without Archimedean axioms. Philosophy of Science 41(4):374–393.10.1086/288600Search in Google Scholar

Niederée, R. 1992. What do numbers measure?: A new approach to fundamental measurement. Mathematical Social Sciences 24(2-3):237–276.10.1016/0165-4896(92)90063-BSearch in Google Scholar

Plato. 1997. Protagoras. In Cooper, J. M.; Hutchinson, D. S.; et al., eds., Plato: complete works. Hackett Publishing.Search in Google Scholar

Pohlers, W. 2008. Proof theory: The first step into impredicativity. Springer.Search in Google Scholar

Rathjen, M. 2006. The art of ordinal analysis. In Proceedings of the International Congress of Mathematicians, volume 2, 45–69.Search in Google Scholar

Reeder, P. F. 2012. Infinitesimals for Metaphysics: Consequences for the Ontologies of Space and Time. Ph.D. Dissertation, The Ohio State University.Search in Google Scholar

Rizza, D. 2016. Divergent Mathematical Treatments in Utility Theory. Erkenntnis 81(6):1287–1303.10.1007/s10670-015-9795-1Search in Google Scholar

Robinson, A. 1974. Non-standard analysis. Princeton University Press.Search in Google Scholar

Rosinger, E. E. 2007. Cosmic Contact: To Be, or Not To Be Archimedean? arXiv preprint physics/0702206.Search in Google Scholar

Skala, H. J. 1975. Non-Archimedean utility theory. D. Reidel Publishing.10.1007/978-94-010-1724-4Search in Google Scholar

Spearman, C. 1927. The abilities of man. Macmillan.Search in Google Scholar

Tall, D. 1980. Looking at graphs through infinitesimal microscopes, windows and telescopes. The Mathematical Gazette 64:22–49.10.2307/3615886Search in Google Scholar

Veldhuizen, T. L. 2003. C++ Templates are Turing Complete. Technical report, Indiana University.Search in Google Scholar

Wang, P., and Hammer, P. 2015. Assumptions of decision-making models in AGI. In International Conference on Artificial General Intelligence, 197–207. Springer.10.1007/978-3-319-21365-1_21Search in Google Scholar

Wirth, C.; Akrour, R.; Neumann, G.; and Fürnkranz, J. 2017. A survey of preference-based reinforcement learning methods. The Journal of Machine Learning Research 18(1):4945–4990.Search in Google Scholar

Zhao, Y.; Kosorok, M. R.; and Zeng, D. 2009. Reinforcement learning design for cancer clinical trials. Statistics in medicine 28(26):3294–3315.10.1002/sim.3720276741819750510Search in Google Scholar