Reflective Oracles: A Foundation for Classical Game Theory

Classical game theory treats players as special---a description of a game contains a full, explicit enumeration of all players---even though in the real world, "players" are no more fundamentally special than rocks or clouds. It isn't trivial to find a decision-theoretic foundation for game theory in which an agent's coplayers are a non-distinguished part of the agent's environment. Attempts to model both players and the environment as Turing machines, for example, fail for standard diagonalization reasons. In this paper, we introduce a "reflective" type of oracle, which is able to answer questions about the outputs of oracle machines with access to the same oracle. These oracles avoid diagonalization by answering some queries randomly. We show that machines with access to a reflective oracle can be used to define rational agents using causal decision theory. These agents model their environment as a probabilistic oracle machine, which may contain other agents as a non-distinguished part. We show that if such agents interact, they will play a Nash equilibrium, with the randomization in mixed strategies coming from the randomization in the oracle's answers. This can be seen as providing a foundation for classical game theory in which players aren't special.

[1]  G. C. Tiao,et al.  Bayesian inference in statistical analysis , 1973 .

[2]  M. Dufwenberg Game theory. , 2011, Wiley interdisciplinary reviews. Cognitive science.

[3]  Thomas G. Dietterich,et al.  Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter , 2015, AI Mag..

[4]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969, The Mathematical Gazette.

[5]  K. Fan Fixed-point and Minimax Theorems in Locally Convex Topological Linear Spaces. , 1952, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Haim Gaifman,et al.  Reasoning with Limited Resources and Assigning Probabilities to Arithmetical Statements , 2004, Synthese.

[7]  Marcus Hutter,et al.  Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability (Texts in Theoretical Computer Science. An EATCS Series) , 2006 .

[8]  J. Schreiber Foundations Of Statistics , 2016 .

[9]  B. Jones BOUNDED RATIONALITY , 1999 .

[10]  Marcus Hutter,et al.  Universal Artificial Intellegence - Sequential Decisions Based on Algorithmic Probability , 2005, Texts in Theoretical Computer Science. An EATCS Series.

[11]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[12]  Ken Binmore,et al.  Modeling Rational Players: Part I , 1987, Economics and Philosophy.

[13]  Benja Fallenstein,et al.  Aligning Superintelligence with Human Interests: A Technical Research Agenda , 2015 .

[14]  Kevin B. Korb,et al.  Bayesian Artificial Intelligence , 2004, Computer science and data analysis series.

[15]  S. Pfeifer A Course In Microeconomic Theory , 2016 .

[16]  E. Eells Causal Decision Theory , 1984, PSA: Proceedings of the Biennial Meeting of the Philosophy of Science Association.

[17]  C. Robert Superintelligence: Paths, Dangers, Strategies , 2017 .

[18]  Benja Fallenstein,et al.  Reflective Oracles: A Foundation for Game Theory in Artificial Intelligence , 2015, LORI.

[19]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..

[20]  Laurent Orseau,et al.  Space-Time Embedded Intelligence , 2012, AGI.