Maxims for Machines: Manipulating Kant’s Universal Laws with Inverse Reinforcement Learning | AI and Ethics

Machine Learning


  • Practical Philosophy, translated by Gregor M. Contents: The answer to the question: What is Enlightenment?, Foundations of the Metaphysics of Morals, Critique of Practical Reason, Metaphysics of Morals. Practical Philosophy (1996)

  • Kant, I.: Grounds of the Metaphysics of Morals. Translated by J.W. Ellington. Indianapolis: Hackett Publishers. (1993/1785)

  • Allison, H.: Kant’s Foundations for the Metaphysics of Morals: An Commentary. Oxford University Press, Oxford (2011)

    Reserve Google Scholar

  • Askell, A. et al.: General language assistants as laboratories for coordination. Preprint available at https://arxiv.org/abs/2112.00861 (2021)

  • Cecchini, D., Pflanzer, M., Dubljević, V.: Coordination of artificial intelligence and moral intuition: An intuitionist approach to the coordination problem. Ethics of AI. https://doi.org/10.1007/s43681-024-00496-5 (2024).

    Article Google Scholar

  • Chaly, V.: Kantian fallibilist ethics for AI coordination. J. Philos. I’ll investigate. 18(47), 303–318 (2024)

    Google Scholar

  • Dancy, J.: Ethics without principles. Oxford University Press, Oxford (2004)

    Reserve Google Scholar

  • Deligiorgi, K.: The Scope of Autonomy: Kant and the Morality of Freedom. Oxford University Press, Oxford (2012)

    Reserve Google Scholar

  • Feldman, F.: Kantian Ethics. Reference: Introduction to Ethics, pages 97-117. Prentice Hall, New York (1978)

    Google Scholar

  • Gabriel, I.: Artificial intelligence, values, and coordination. heart. Mach. 30411–437 (2020)

    Article Google Scholar

  • Geiger I.: How are the various formulas of the categorical imperative related? Reverend Kant 20(3), 395–419 (2015)

    Article MathSciNet Google Scholar

  • Guyer, P.: Kant’s Foundations for the Metaphysics of Morals: A Reader’s Guide. Continuum, New York (2007)

    Google Scholar

  • Herman, B.: The Practice of Moral Judgment. Harvard University Press, Cambridge (1993)

    Google Scholar

  • Johnson, R., Cureton, A.: Kant’s Moral Philosophy. Published in: Zalta EN, Uri N. (eds.) Stanford Encyclopedia of Philosophy (Fall 2022 Edition) https://plato.stanford.edu/archives/fall2022/entries/kant-moral/ (2022)

  • Korsgaard, CM: Kant’s formulation of universal laws. pack. Philos. Q. 6624–47 (1985)

    Article Google Scholar

  • Manna, R., Nath, R.: Kant’s moral agency and the ethics of artificial intelligence. problem 100139–151 (2024)

    Article Google Scholar

  • Mougan, C., Jason B.: Linking Kantian deontology and AI: Towards morally robust fairness metrics. Preprint available at https://arxiv.org/abs/2311.05227 (2024)

  • Ng, AY, Russell, SJ: Algorithms for inverse reinforcement learning. Published in: Proceedings of the 17th International Conference on Machine Learning (ICML). San Francisco: Morgan Kaufman, pp. 663–670 (2000)

  • O’Neill, O.: Act on principles. Columbia University Press, New York (1975)

    Google Scholar

  • O’Neill, O.: The Construction of Reason. Cambridge University Press, New York (1989)

    Google Scholar

  • Rawls, J.: Kantian constructivism in moral theory. J. Philos. 77, 515–572. Reprinted in Collected Papers, Cambridge, MA: Harvard University Press, 303–358, 1999 (1980)

  • Rawls, J.: Themes of Kant’s Moral Philosophy. Reference: Förster, E. (ed.), Kant’s Transcendental Deduction, pp. 81-113. Stanford University Press, Stanford (1989)

    Google Scholar

  • Rawls, J.: Lectures on the History of Moral Philosophy. Barbara H. (Ed.). Harvard University Press, Cambridge (2000)

  • Russell, S.: Compatibility with humans: AI and control issues. Allen Lane, Bristol (2019)

    Google Scholar

  • Sanwoolu, O.: Kantian deontology for AI: Integrity without moral agency. AI ethics 55425–5437 (2025). https://doi.org/10.1007/s43681-025-00784-8

    Article Google Scholar

  • Stoll, K.: Free Choice: A Kantian Guide to Life. Oxford University Press, Oxford (2022)

    Reserve Google Scholar

  • Sutton, RS, Barto, AG: Reinforcement Learning: An Introduction, 2nd edition. MIT Press, Cambridge (2017)

    Google Scholar

  • Timmerman, J.: Foundations of Kant’s Moral Metaphysics: An Commentary. Cambridge University Press, Cambridge (2007)

    Reserve Google Scholar

  • Timmons, M. (ed.): Moral Theory: An Introduction. Rowman and Littlefield Publishers, Lanham (2013)

    Google Scholar

  • Morrison, I.: On Kant’s Maxims: Reconciling the Incorporation Thesis and Weakness of the Will. Historical philosopher. Q. twenty two(1), 73–89 (2005)

    Google Scholar



  • Source link