2 Search Results for "Akian, Marianne"

Document
DOI: 10.4230/LIPIcs.MFCS.2023.10
Solving Irreducible Stochastic Mean-Payoff Games and Entropy Games by Relative Krasnoselskii-Mann Iteration

Authors: Marianne Akian, Stéphane Gaubert, Ulysse Naepels, and Basile Terver

Published in: LIPIcs, Volume 272, 48th International Symposium on Mathematical Foundations of Computer Science (MFCS 2023)

Abstract
We analyse an algorithm solving stochastic mean-payoff games, combining the ideas of relative value iteration and of Krasnoselskii-Mann damping. We derive parameterized complexity bounds for several classes of games satisfying irreducibility conditions. We show in particular that an ε-approximation of the value of an irreducible concurrent stochastic game can be computed in a number of iterations in O(|log(ε)|) where the constant in the O(⋅) is explicit, depending on the smallest non-zero transition probabilities. This should be compared with a bound in O(ε^{-1}|log(ε)|) obtained by Chatterjee and Ibsen-Jensen (ICALP 2014) for the same class of games, and to a O(ε^{-1}) bound by Allamigeon, Gaubert, Katz and Skomra (ICALP 2022) for turn-based games. We also establish parameterized complexity bounds for entropy games, a class of matrix multiplication games introduced by Asarin, Cervelle, Degorre, Dima, Horn and Kozyakin. We derive these results by methods of variational analysis, establishing contraction properties of the relative Krasnoselskii-Mann iteration with respect to Hilbert’s semi-norm.
Cite as

Marianne Akian, Stéphane Gaubert, Ulysse Naepels, and Basile Terver. Solving Irreducible Stochastic Mean-Payoff Games and Entropy Games by Relative Krasnoselskii-Mann Iteration. In 48th International Symposium on Mathematical Foundations of Computer Science (MFCS 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 272, pp. 10:1-10:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{akian_et_al:LIPIcs.MFCS.2023.10,
  author =	{Akian, Marianne and Gaubert, St\'{e}phane and Naepels, Ulysse and Terver, Basile},
  title =	{{Solving Irreducible Stochastic Mean-Payoff Games and Entropy Games by Relative Krasnoselskii-Mann Iteration}},
  booktitle =	{48th International Symposium on Mathematical Foundations of Computer Science (MFCS 2023)},
  pages =	{10:1--10:15},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-292-1},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{272},
  editor =	{Leroux, J\'{e}r\^{o}me and Lombardy, Sylvain and Peleg, David},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.MFCS.2023.10},
  URN =		{urn:nbn:de:0030-drops-185448},
  doi =		{10.4230/LIPIcs.MFCS.2023.10},
  annote =	{Keywords: Stochastic mean-payoff games, concurrent games, entropy games, relative value iteration, Krasnoselskii-Mann fixed point algorithm, Hilbert projective metric}
}
Document
DOI: 10.4230/LIPIcs.STACS.2017.6
The Operator Approach to Entropy Games

Authors: Marianne Akian, Stéphane Gaubert, Julien Grand-Clément, and Jérémie Guillaud

Published in: LIPIcs, Volume 66, 34th Symposium on Theoretical Aspects of Computer Science (STACS 2017)

Abstract
Entropy games and matrix multiplication games have been recently introduced by Asarin et al. They model the situation in which one player (Despot) wishes to minimize the growth rate of a matrix product, whereas the other player (Tribune) wishes to maximize it. We develop an operator approach to entropy games. This allows us to show that entropy games can be cast as stochastic mean payoff games in which some action spaces are simplices and payments are given by a relative entropy (Kullback-Leibler divergence). In this way, we show that entropy games with a fixed number of states belonging to Despot can be solved in polynomial time. This approach also allows us to solve these games by a policy iteration algorithm, which we compare with the spectral simplex algorithm developed by Protasov.
Cite as

Marianne Akian, Stéphane Gaubert, Julien Grand-Clément, and Jérémie Guillaud. The Operator Approach to Entropy Games. In 34th Symposium on Theoretical Aspects of Computer Science (STACS 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 66, pp. 6:1-6:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{akian_et_al:LIPIcs.STACS.2017.6,
  author =	{Akian, Marianne and Gaubert, St\'{e}phane and Grand-Cl\'{e}ment, Julien and Guillaud, J\'{e}r\'{e}mie},
  title =	{{The Operator Approach to Entropy Games}},
  booktitle =	{34th Symposium on Theoretical Aspects of Computer Science (STACS 2017)},
  pages =	{6:1--6:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-028-6},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{66},
  editor =	{Vollmer, Heribert and Vall\'{e}e, Brigitte},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.STACS.2017.6},
  URN =		{urn:nbn:de:0030-drops-70260},
  doi =		{10.4230/LIPIcs.STACS.2017.6},
  annote =	{Keywords: Stochastic games, Shapley operators, policy iteration, Perron eigenvalues, Risk sensitive control}
}
  • Refine by Author
  • 2 Akian, Marianne
  • 2 Gaubert, Stéphane
  • 1 Grand-Clément, Julien
  • 1 Guillaud, Jérémie
  • 1 Naepels, Ulysse
  • Show More...

  • Refine by Classification
  • 1 Theory of computation → Algorithmic game theory

  • Refine by Keyword
  • 1 Hilbert projective metric
  • 1 Krasnoselskii-Mann fixed point algorithm
  • 1 Perron eigenvalues
  • 1 Risk sensitive control
  • 1 Shapley operators
  • Show More...

  • Refine by Type
  • 2 document

  • Refine by Publication Year
  • 1 2017
  • 1 2023

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact