• Corpus ID: 15228099

Reflective Oracles: A Foundation for Classical Game Theory

@article{Fallenstein2015ReflectiveOA,
  title={Reflective Oracles: A Foundation for Classical Game Theory},
  author={Benja Fallenstein and Jessica Taylor and Paul Francis Christiano},
  journal={ArXiv},
  year={2015},
  volume={abs/1508.04145}
}
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… 
Reflective Oracles: A Foundation for Game Theory in Artificial Intelligence
TLDR
This paper proposes 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.
Reflective Variants of Solomonoff Induction and AIXI
TLDR
It is shown that reflective Solomonoff induction and AIXI can themselves be implemented as oracle machines with access to a reflective oracle, making it possible for them to model environments that contain reasoners as powerful as themselves.
A Formal Solution to the Grain of Truth Problem
TLDR
A formal and general solution to the full grain of truth problem is presented: a class of policies is constructed that contains all computable policies as well as Bayes-optimal policies for every lower semicomputable prior over the class.
Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, UAI 2016, June 25-29, 2016, New York City, NY, USA
TLDR
This paper presents a new gradient-based approach for solving large Stackelberg games in security settings, and demonstrates that it can have negligible regret against the leader’s true equilibrium strategy, while scaling to large games.
Nonparametric General Reinforcement Learning
TLDR
It is proved that Thompson sampling is asymptotically optimal in stochastic environments in the sense that its value converges to the value of the optimal policy, and Thompson sampling achieves sublinear regret in these environments.

References

SHOWING 1-10 OF 29 REFERENCES
Reflective Oracles: A Foundation for Game Theory in Artificial Intelligence
TLDR
This paper proposes 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.
Modeling Rational Players: Part I
Game theory has proved a useful tool in the study of simple economic models. However, numerous foundational issues remain unresolved. The situation is particularly confusing in respect of the
BOUNDED RATIONALITY
Findings from behavioral organization theory, behavioral decision theory, survey research, and experimental economics leave no doubt about the failure of rational choice as a descriptive model of
Theory of Recursive Functions and Effective Computability
If searching for the ebook by Hartley Rogers Theory of Recursive Functions and Effective Computability in pdf format, then you've come to the faithful site. We presented the complete version of this
Game theory.
  • M. Dufwenberg
  • Psychology
    Wiley interdisciplinary reviews. Cognitive science
  • 2011
TLDR
The nature of game-theoretic analysis, the history of game theory,Why game theory is useful for understanding human psychology, and why game theory has played a key role in the recent explosion of interest in the field of behavioral economics are discussed.
Space-Time Embedded Intelligence
TLDR
This paper presents the first formal measure of intelligence for agents fully embedded within their environment that merges and goes beyond Legg's and Russell's, leading to a new, more realistic definition of artificial intelligence that is called Space-Time Embedded Intelligence.
A Course In Microeconomic Theory
Letter to the Editor: Research Priorities for Robust and Beneficial Artificial Intelligence: An Open Letter
TLDR
It is believed that research on how to make AI systems robust and beneficial is both important and timely, and that there are concrete research directions that can be pursued today.
Universal Artificial Intellegence - Sequential Decisions Based on Algorithmic Probability
  • Marcus Hutter
  • Education
    Texts in Theoretical Computer Science. An EATCS Series
  • 2005
TLDR
Reading a book as this universal artificial intelligence sequential decisions based on algorithmic probability and other references can enrich your life quality.
...
1
2
3
...