×

Reflective oracles: a foundation for game theory in artificial intelligence. (English) Zbl 1471.68269

van der Hoek, Wiebe (ed.) et al., Logic, rationality, and interaction. 5th international workshop, LORI 2015, Taipei, Taiwan, October 28–30, 2015. Proceedings. Berlin: Springer. Lect. Notes Comput. Sci. 9394, 411-415 (2015).
Summary: Game theory treats players as special: a description of a game contains a full, explicit enumeration of all players. This isn’t a realistic assumption for autonomous intelligent agents. In this paper, we propose a framework in which agents and their environments are both modelled as probablistic oracle machines with access to a “reflective” oracle, which is able to answer questions about the outputs of other machines with access to the same oracle. These oracles avoid diagonalization problems by answering some queries randomly. Agents make decisions by asking the oracle questions about their environment, which they model as an arbitrary oracle machines. Since agents are themselves oracle machines, the environment can contain other agents as non-distinguished subprocesses, removing the special treatment of players in the classical theory. We show that agents interacting in this way play Nash equilibria.
For the entire collection see [Zbl 1325.68024].

MSC:

68T27 Logic in artificial intelligence
91A80 Applications of game theory
Full Text: DOI

References:

[1] Binmore, K.: Modeling rational players: Part I. Economics and Philosophy 3(02), 179–214 (1987) · doi:10.1017/S0266267100002893
[2] Fallenstein, B., Soares, N., Taylor, J.: Reflective variants of Solomonoff induction and AIXI. In: Bieger, J., Goertzel, B., Potapov, A. (eds.) AGI 2015. LNCS, vol. 9205, pp. 60–69. Springer, Heidelberg (2015) · doi:10.1007/978-3-319-21365-1_7
[3] Fallenstein, B., Taylor, J., Christiano, P.: Reflective oracles: A foundation for classical game theory. Tech. rep., Machine Intelligence Research Institute (2015), http://intelligence.org/files/ReflectiveOracles.pdf · Zbl 1471.68269
[4] Hutter, M.: Universal Artificial Intelligence. Texts in Theoretical Computer Science. Springer (2005) · Zbl 1099.68082 · doi:10.1007/b138233
[5] Kreps, D.M.: A Course in Microeconomic Theory. Princeton University Press (1990)
[6] Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw-Hill (1967) · Zbl 0183.01401
[7] Solomonoff, R.J.: A formal theory of inductive inference. Part I 7(1), 1–22 (1964) · Zbl 0258.68045
[8] Weirich, P.: Causal decision theory. In: Zalta, E.N. (ed.) The Stanford Encyclopedia of Philosophy (2012)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.