中文
相关论文

相关论文: Policy iteration for perfect information stochasti…

200 篇论文

We study the computational complexity of approximating general constrained Markov decision processes. Our primary contribution is the design of a polynomial time $(0,\epsilon)$-additive bicriteria approximation algorithm for finding optimal…

数据结构与算法 · 计算机科学 2025-02-12 Jeremy McMahan

In this paper, we consider a zero-sum undiscounted stochastic game which has finite state space and finitely many pure actions. Also, we assume the transition probability of the undiscounted stochastic game is controlled by one player and…

最优化与控制 · 数学 2022-09-23 Purba Das , T. Parthasarathy , G Ravindran

Convergence of the policy iteration method for discrete and continuous optimal control problems holds under general assumptions. Moreover, in some circumstances, it is also possible to show a quadratic rate of convergence for the algorithm.…

最优化与控制 · 数学 2022-03-02 Fabio Camilli , Qing Tang

Mean-payoff zero-sum stochastic games can be studied by means of a nonlinear spectral problem. When the state space is finite, the latter consists in finding an eigenpair $(u,\lambda)$ solution of $T(u)=\lambda e + u$, where $T:\mathbb{R}^n…

最优化与控制 · 数学 2019-12-30 Marianne Akian , Stéphane Gaubert , Antoine Hochart

We study the computational complexity of solving stochastic games with mean-payoff objectives. Instead of identifying special classes in which simple strategies are sufficient to play $\epsilon$-optimally, or form $\epsilon$-Nash…

计算机科学与博弈论 · 计算机科学 2024-05-16 Sougata Bose , Rasmus Ibsen-Jensen , Patrick Totzke

Stochastic games are a classical model in game theory in which two opponents interact and the environment changes in response to the players' behavior. The central solution concepts for these games are the discounted values and the value,…

最优化与控制 · 数学 2019-12-12 Miquel Oliu-Barton

We consider the general model of zero-sum repeated games (or stochastic games with signals), and assume that one of the players is fully informed and controls the transitions of the state variable. We prove the existence of the uniform…

最优化与控制 · 数学 2009-04-20 Jérôme Renault

Recently, Sidford, Wang, Wu and Ye (2018) developed an algorithm combining variance reduction techniques with value iteration to solve discounted Markov decision processes. This algorithm has a sublinear complexity when the discount factor…

最优化与控制 · 数学 2019-09-16 Marianne Akian , Stéphane Gaubert , Zheng Qu , Omar Saadi

We consider two-person zero-sum stochastic mean payoff games with perfect information, or BWR-games, given by a digraph $G = (V, E)$, with local rewards $r: E \to \ZZ$, and three types of positions: black $V_B$, white $V_W$, and random…

计算机科学与博弈论 · 计算机科学 2017-03-27 Endre Boros , Khaled Elbassioni , Vladimir Gurvich , Kazuhisa Makino

We consider two-person zero-sum stochastic mean payoff games with perfect information, or BWR-games, given by a digraph $G = (V, E)$, with local rewards $r: E \to \ZZ$, and three types of positions: black $V_B$, white $V_W$, and random…

数据结构与算法 · 计算机科学 2016-10-24 Endre Boros , Khaled Elbassioni , Vladimir Gurvich , Kazuhisa Makino

We study a model of games that combines concurrency, imperfect information and stochastic aspects. Those are finite states games in which, at each round, the two players choose, simultaneously and independently, an action. Then a successor…

形式语言与自动机理论 · 计算机科学 2011-08-31 Vincent Gripon , Olivier Serre

We consider a deterministic mean field games problem in which a typical agent solves an optimal control problem where the dynamics is affine with respect to the control and the cost functional has a growth which is polynomial with respect…

最优化与控制 · 数学 2023-05-03 Justina Gianatti , Francisco J. Silva , Ahmad Zorkot

Decision-making problems in uncertain or stochastic domains are often formulated as Markov decision processes (MDPs). Policy iteration (PI) is a popular algorithm for searching over policy-space, the size of which is exponential in the…

人工智能 · 计算机科学 2013-01-30 Yishay Mansour , Satinder Singh

We propose a policy iteration method to solve an inverse problem for a mean-field game (MFG) model, specifically to reconstruct the obstacle function in the game from the partial observation data of value functions, which represent the…

最优化与控制 · 数学 2026-02-12 Kui Ren , Nathan Soedjak , Shanyin Tong

We develop value iteration-based algorithms to solve in a unified manner different classes of combinatorial zero-sum games with mean-payoff type rewards. These algorithms rely on an oracle, evaluating the dynamic programming operator up to…

计算机科学与博弈论 · 计算机科学 2024-11-12 Xavier Allamigeon , Stéphane Gaubert , Ricardo D. Katz , Mateusz Skomra

This paper considers an infinitely repeated three-player Bayesian game with lack of information on two sides, in which an informed player plays two zero-sum games simultaneously at each stage against two uninformed players. This is a…

理论经济学 · 经济学 2023-03-10 Lucas Pahl

We present a deterministic algorithm, solving discounted games with $n$ nodes in $n^{O(1)}\cdot (2 + \sqrt{2})^n$-time. For bipartite discounted games our algorithm runs in $n^{O(1)}\cdot 2^n$-time. Prior to our work no deterministic…

数据结构与算法 · 计算机科学 2020-10-27 Alexander Kozachinskiy

A zero-sum two person Perfect Information Stochastic game (PISG) under limiting average payoff has a value and both the maximiser and the minimiser have optimal pure stationary strategies. Firstly we form the matrix of undiscounted payoffs…

最优化与控制 · 数学 2023-02-15 K. G. Bakshi , S. Sinha

Quantitative games are two-player zero-sum games played on directed weighted graphs. Total-payoff games (that can be seen as a refinement of the well-studied mean-payoff games) are the variant where the payoff of a play is computed as the…

计算机科学与博弈论 · 计算机科学 2015-07-15 Thomas Brihaye , Gilles Geeraerts , Axel Haddad , Benjamin Monmege

The paper proposes a natural measure space of zero-sum perfect information games with upper semicontinuous payoffs. Each game is specified by the game tree, and by the assignment of the active player and of the capacity to each node of the…

计算机科学与博弈论 · 计算机科学 2021-04-22 János Flesch , Arkadi Predtetchinski , Ville Suomala