Abstract
It has recently been shown that a Bayesian agent with a universal hypothesis class resolves most induction problems discussed in the philosophy of science. These ideal agents are, however, neither practical nor a good model for how real science works. We here introduce a framework for learning based on implicit beliefs over all possible hypotheses and limited sets of explicit theories sampled from an implicit distribution represented only by the process by which it generates new hypotheses. We address the questions of how to act based on a limited set of theories as well as what an ideal sampling process should be like. Finally, we discuss topics in philosophy of science and cognitive science from the perspective of this framework.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
- Feature Vector
- Bayesian Inference
- Reinforcement Learning
- Inductive Logic Programming
- Kolmogorov Complexity
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Asmuth, J., Li, L., Littman, M.L., Nouri, A., Wingate, D.: A bayesian sampling approach to exploration in reinforcement learning. In: Uncertainty in Artificial Intelligence (UAI), pp. 19–26 (2009)
Anderson, J.R.: Is human cognition adaptive? Behavioral & Brain Sciences 14(3), 471–517 (1991)
Berg, B.A.: Markov Chain Monte Carlo Simulations And Their Statistical Analysis: With Web-based Fortran Code. World Scientific Publishing Company (2004)
Box, G.E.P., Tiao, G.C.: Bayesian Inference in Statistical Analysis (Wiley Classics Library). Wiley-Interscience (1992)
Casella, G., George, E.I.: Explaining the gibbs sampler. The American Statistician 46(3), 167–174 (1992)
Demski, A.: Logical prior probability. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 50–59. Springer, Heidelberg (2012)
Edwards, W.: Conservatism in human information processing. In: Formal Representation of Human Judgment, pp. 17–52 (1968)
Griffiths, T.L., Kemp, C., Tenenbaum, J.B.: Bayesian Models of Cognition. Cambridge University Press (2008)
Good, I.J.: A Bayesian approach in the philosophy of inference. British Journal for the Philosophy of Science, 161–166 (1984)
Gaifman, H., Snir, M.: Probabilities over rich languages, testing and randomness. J. Symb. Log. 47(3), 495–548 (1982)
Griffiths, T.L., Tenenbaum, J.B.: Theory-based causal induction. Psychological Review 116(4), 661–716 (2009)
Hanson, N.R.: Patterns of Discovery. Cambridge University Press, Cambridge (1958)
Hutter, M., Lloyd, J.W., Ng, K.S., Uther, W.T.B.: Probabilities on sentences in an expressive logic. Journal of Applied Probability (2013)
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press (1975)
Howson, C., Urbach, P.: Scientific Reasoning: The Bayesian Approach, 3rd edn., Open Court (2005)
Hutter, M.: Universal Articial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin (2005)
Hutter, M.: On universal prediction and bayesian confirmation. Theoretical Computer Science 384, 33–48 (2007)
Hutter, M.: Feature reinforcement learning: Part I. Unstructured MDPs. Journal of General Artificial Intelligence (2009)
Hutter, M.: The subjective computable universe. In: A Computable Universe: Understanding and Exploring Nature as Computation, pp. 399–416. World Scientific (2012)
Jaynes, E.T.: Probability Theory: The Logic of Science. Cambridge University Press (2003)
Kahneman, D., Tversky, A.: Prospect theory: An analysis of decision under risk. Econometrica 47, 263–291 (1979)
Kemp, C., Tenenbaum, J.B., Niyogi, S., Griffiths, T.L.: A probabilistic model of theory formation. Cognition 114(2) (2010)
Kuhn, T.S.: The structure of scientific revolutions. University of Chicago Press (1970)
Lattimore, T., Hutter, M.: Asymptotically optimal agents. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol. 6925, pp. 368–382. Springer, Heidelberg (2011)
Li, M., Vitany, P.: An Introduction to Kolmogov Complexity and Its Applications. Springer (1993)
Muggleton, S.: Inductive logic programming. New Generation Computing 8(4), 295–318 (1991)
Nestler, S., Blank, H., von Collani, G.: Hindsight bias doesn’t always come easy: Causal models, cognitive effort, and creeping determinism. Journal of Experimental Psychology: Learning 34(5) (2008)
Nyarko, Y.: The savage-bayesian foundations of economic dynamics. Working Papers 93-35, C.V. Starr Center for Applied Economics, New York University (1993)
Orseau, L., Lattimore, T.: Univeral knowledge-seeking agents for stochastic environments (submitted, 2013)
Osborne, M.J., Rubinstein, A.: A Course in Game Theory. MIT Press Books. The MIT Press (1994)
Orseau, L.: Universal knowledge-seeking agents. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol. 6925, pp. 353–367. Springer, Heidelberg (2011)
Rechenberg, I.: Evolutionsstrategie. Frommann-Holzboog-Verlag (1971)
Rathmanner, S., Hutter, M.: A philosophical treatise of universal induction. Entropy 13(6), 1076–1136 (2011)
Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach, 3rd edn. Prentice Hall, Englewood Cliffs (2010)
Robert, C.P.: The Bayesian choice: a decision-theoretic motivation. Springer, New York (1994)
Savage, L.: The Foundations of Statistics. Wiley, New York (1954)
Sunehag, P., Hutter, M.: Axioms for rational reinforcement learning. In: Kivinen, J., Szepesvári, C., Ukkonen, E., Zeugmann, T. (eds.) ALT 2011. LNCS, vol. 6925, pp. 338–352. Springer, Heidelberg (2011)
Sunehag, P., Hutter, M.: Optimistic agents are asymptotically optimal. In: Thielscher, M., Zhang, D. (eds.) AI 2012. LNCS, vol. 7691, pp. 15–26. Springer, Heidelberg (2012)
Sunehag, P., Hutter, M.: Rational general reinforcement learning (submitted, 2013)
Solomonoff, R.J.: A formal theory of inductive inference. Part i and ii. Information and Control 7(1,2), 1–22, 224–254 (1964)
Kyle Stanford, P.: Exceeding Our Grasp: Science, History, and the Problem of Unconceived Alternatives. Oxford University Press (2006)
Strens, M.J.A.: A bayesian framework for reinforcement learning. In: Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), pp. 943–950 (2000)
Strevens, M.: The bayesian approach to the philosophy of science. In: Encyclopedia of Philosophy, 2nd edn. (2006)
Tenenbaum, J.B., Kemp, C., Griffiths, T.L., Goodman, N.D.: How to Grow a Mind: Statistics, Structure, and Abstraction. Science 331(6022), 1279–1285 (2011)
Weinstein, N.D.: Unrealistic optimism about future life events. Journal of Personality and Social Psychology 39(5), 806–820 (1980)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sunehag, P., Hutter, M. (2013). Learning Agents with Evolving Hypothesis Classes. In: Kühnberger, KU., Rudolph, S., Wang, P. (eds) Artificial General Intelligence. AGI 2013. Lecture Notes in Computer Science(), vol 7999. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39521-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-642-39521-5_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39520-8
Online ISBN: 978-3-642-39521-5
eBook Packages: Computer ScienceComputer Science (R0)