Abstract
Finding the universal artificial intelligent agent is the old dream of AI scientists. Solomonoff Induction was one big step towards this, giving a universal solution to the general problem of Sequence Prediction, by defining a universal prior distribution. Hutter defined AIXI, which extends the latter to the Reinforcement Learning framework, where almost all if not all AI problems can be formulated. However, new difficulties arise, because the agent is now active, whereas it is only passive in the Sequence Prediction case. This makes proving AIXI’s optimality difficult. In fact, we prove that the current definition of AIXI can sometimes be only suboptimal in a certain sense, and we generalize this result to infinite horizon agents and to any static prior distribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cohen, J.D., McClure, S.M., Yu, A.J.: Should I stay or should I go? How the human brain manages the trade-off between exploitation and exploration. Philosophical Transactions of the Royal Society B: Biological Sciences 362(1481), 933–942 (2007)
Hutter, M.: A theory of universal artificial intelligence based on algorithmic complexity. Arxiv (April 2000), http://arxiv.org/abs/cs/0004001
Hutter, M.: Self-optimizing and pareto-optimal policies in general environments based on bayes-mixtures. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 364–379. Springer, Heidelberg (2002)
Hutter, M.: Universal Artificial Intelligence: Sequential Decisions Based On Algorithmic Probability. Springer, Heidelberg (2005)
Hutter, M.: Universal algorithmic intelligence: A mathematical top-down approach. In: Artificial General Intelligence, pp. 227–290. Springer, Heidelberg (2007)
Kraft, L.G.: A device for quantizing, grouping, and coding amplitude modulated pulses. Ph.D. thesis, MIT, Electrical Engineering Department, Cambridge, MA (1949)
Li, M., Vitanyi, P.: An Introduction to Kolmogorov Complexity and Its Applications. Springer, New York (2008)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2003)
Schmidhuber, J.: The speed prior: A new simplicity measure yielding near-optimal computable predictions. In: Kivinen, J., Sloan, R.H. (eds.) COLT 2002. LNCS (LNAI), vol. 2375, pp. 216–228. Springer, Heidelberg (2002)
Solomonoff, R.: Complexity-based induction systems: comparisons and convergence theorems. IEEE Transactions on Information Theory 24(4), 422–432 (1978)
Solomonoff, R.J.: A formal theory of inductive inference. Part I. Information and Control 7, 1–22 (1964)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998); a Bradford Book
Veness, J., Ng, K.S., Hutter, M., Silver, D.: A monte carlo AIXI approximation. Arxiv (September 2009), http://arxiv.org/abs/0909.0801
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Orseau, L. (2010). Optimality Issues of Universal Greedy Agents with Static Priors. In: Hutter, M., Stephan, F., Vovk, V., Zeugmann, T. (eds) Algorithmic Learning Theory. ALT 2010. Lecture Notes in Computer Science(), vol 6331. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-16108-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-16108-7_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-16107-0
Online ISBN: 978-3-642-16108-7
eBook Packages: Computer ScienceComputer Science (R0)