Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 38 min ago
PreprintarXiv licencearXiv

Feedback autocratic strategies in stochastic games

  • Masahiko Ueda
Open at sourcePDFDOICite

Abstract

A stochastic game is an optimal control problem for multiple agents in a stochastic environment. Stochastic games contain important practical problems, related to environmental issues or traffic flows. If the number of environmental states is one, such stochastic games are called repeated games. In repeated games, several strategies which unilaterally control payoffs have been proposed, and these strategies work in a mechanism similar to feedback control. In this paper, we generalize these strategies as feedback strategies in stochastic games, and investigate their properties. In particular, we provide a necessary and sufficient condition for such feedback strategies to work as controllers of payoffs under some assumptions. We demonstrate the performance of such feedback strategies in several examples related to social dilemmas. Our findings connect the theory of payoff control in repeated games to the theory of feedback control in stochastic games.

Related

  1. Performance of Zero-determinant Strategies in Repeated Games without Discounting
    Masahiko Ueda
    arXivPreprintarXiv licenceFull textStatistical & nonlinear physicsarXiv
  2. How fast can a parent estimate the value of their children? A quantum algorithm for stochastic games
    Marien Raat, Merlin Incerti-Medici, James R. Wootton +2
    arXivPreprintarXiv licenceFull textQuantum physics & quantum informationarXiv
  3. Multi-Agent Learning of Reactive Strategies in Iterated Games
    James P. Wolfe, Joshua B. Plotkin
    arXivPreprintCC BY 4.0Full textEvolutionary biologyStatistical & nonlinear physicsarXiv
  4. Branching stochastic mechanics: Relative localization and collective poles from Bohm/Fisher feedback
    Benoit Bischoff, Eric Dumonteil
    arXivPreprintarXiv licenceFull textQuantum physics & quantum informationStatistical & nonlinear physicsarXiv
  5. Open-ended innovation arm-race in zero-sum games
    Matteo Marsili
    arXivPreprintCC BY-NC-SA 4.0Full textStatistical & nonlinear physicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{ueda2026feedback,
  title = {{Feedback autocratic strategies in stochastic games}},
  author = {Masahiko Ueda},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.36683},
  eprint = {2610.36683},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.36683},
}
RIS
TY  - UNPB
TI  - Feedback autocratic strategies in stochastic games
AU  - Masahiko Ueda
PY  - 2026
DA  - 2026/10/27
PB  - arXiv
DO  - 10.48550/arxiv.2610.36683
UR  - https://arxiv.org/abs/2610.36683
AB  - A stochastic game is an optimal control problem for multiple agents in a stochastic environment. Stochastic games contain important practical problems, related to environmental issues or traffic flows. If the number of environmental states is one, such stochastic games are called repeated games. In repeated games, several strategies which unilaterally control payoffs have been proposed, and these strategies work in a mechanism similar to feedback control. In this paper, we generalize these strategies as feedback strategies in stochastic games, and investigate their properties. In particular, we provide a necessary and sufficient condition for such feedback strategies to work as controllers of payoffs under some assumptions. We demonstrate the performance of such feedback strategies in several examples related to social dilemmas. Our findings connect the theory of payoff control in repeated games to the theory of feedback control in stochastic games.
ER  -