Pith. sign in

REVIEW 1 cited by

Reflective Oracles: A Foundation for Classical Game Theory

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1508.04145 v1 pith:MGMT4DUO submitted 2015-08-17 cs.AI cs.GT

classification cs.AIcs.GT
keywords oraclegametheoryagentsplayersclassicalenvironmentfoundation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Formalizing Embeddedness Failures in Universal Artificial Intelligence

    cs.AI 2025-05 conditional novelty 6.0 of 10

    Joint AIXI, an embedded variant that treats actions and percepts symmetrically, provably fails to converge on a trivial copy-the-action environment for adversarial action sequences, and its belief does not dominate th...

Pith tools