Recursive joint simulation in games.

Game-theoretic dynamics between AI agents could differ from traditional human–human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is known. Such an agent would then be fundamentally uncertain wheth...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 208; no. 2; pp. 1 - 28
Autores principales: Kovarik, Vojtech, Oesterheld, Caspar, Conitzer, Vincent
Formato: Artículo
Publicado: Springer Nature Aug2026
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=195763681&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 195763681
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00397857
        4LI
      jtl: Synthese
      issn: 00397857
      maglogo: N
    pubinfo:
      dt: Aug2026
      vid: 208
      iid: 2
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        195763681
        10.1007/s11229-026-05706-7
      ppf: 1
      ppct: 27
      formats:
      tig:
        atl: Recursive joint simulation in games.
      aug:
        au:
          Kovarik, Vojtech
          Oesterheld, Caspar
          Conitzer, Vincent
        affil:
          https://ror.org/05x2bcf33 Foundations of Cooperative AI Lab (FOCAL), Computer Science Department, Carnegie Mellon University, 5000 Forbes Avenue, 15213, Pittsburgh, PA, USA
          https://ror.org/03kqpb082 AI Center, Czech Technical University, Jugoslávských partyzánů 1580/3, 160 00, Prague, Czech Republic
          https://ror.org/024d6js02 Center for Theoretical Study, Charles University, Ovocný trh 560/5, 116 36, Prague, Czech Republic
      sug:
      keyword:
        AI agents
        Cooperative AI
        Folk theorem
        Information and Computing Sciences Artificial Intelligence and Image Processing
        Repeated games
        Self-locating beliefs
        Simulation
      ab: Game-theoretic dynamics between AI agents could differ from traditional human–human interactions in various ways. One such difference is that it may be possible to accurately simulate an AI agent, for example because its source code is known. Such an agent would then be fundamentally uncertain whether it is in the real world or in a simulation. Our aim is to explore ways of leveraging this possibility to achieve more cooperative outcomes in strategic settings. In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation. That is, the agents first jointly observe a simulation of the situation they face. This simulation in turn recursively includes additional simulations (with a small chance of failure, to avoid infinite recursion), and the results of all these nested simulations are observed before an action is chosen. We show that the resulting interaction is strategically equivalent to an infinitely repeated version of the original game, allowing a direct transfer of existing results such as the various folk theorems. As evidence that the equivalence is robust, we show that it holds even when we relax some of the assumptions and that it also holds “from the inside” – meaning, for an agent that finds itself inside the game and has self-locating uncertainty.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2026
    holdings:
      @attributes:
        islocal: N