Empirical approximation in Markov games under unbounded payoff: discounted and average criteria
نویسندگان
چکیده
منابع مشابه
An Improved Algorithm for Discounted Payoff Games
We show that an optimal counterstrategy against a fixed positional strategy in a generalized discounted payoff game, where edges have individual discounts, can be computed in O(mn logm) strongly polynomial time, where n and m are the number of vertices and edges in the game graph. This results in the best known strongly subexponential time bound for solving two-player generalized discounted pay...
متن کاملSampling Techniques for Markov Games Approximation Results on Sampling Techniques for Zero-sum, Discounted Markov Games
We extend the “policy rollout” sampling technique for Markov decision processes to Markov games, and provide an approximation result guaranteeing that the resulting sampling-based policy is closer to the Nash equilibrium than the underlying base policy. This improvement is achieved with an amount of sampling that is independent of the state-space size. We base our approximation result on a more...
متن کاملDeterministic Priority Mean-Payoff Games as Limits of Discounted Games
Inspired by the paper of de Alfaro, Henzinger and Majumdar [2] about discounted μ-calculus we show new surprising links between parity games and different classes of discounted games.
متن کاملSimple Stochastic Games, Parity Games, Mean Payoff Games and Discounted Payoff Games Are All LP-Type Problems1
We show that a Simple Stochastic Game (SSG) can be formulated as an LP-type problem. Using this formulation, and the known algorithm of Sharir and Welzl [SW] for LP-type problems, we obtain the first strongly subexponential solution for SSGs (a strongly subexponential algorithm has only been known for binary SSGs [L]). Using known reductions between various games, we achieve the first strongly ...
متن کاملStructural approximations in discounted semi-Markov games
We consider the problem of approximating the values and the equilibria in two-person zero-sum discounted semi-Markov games with in nite horizon and compact action spaces, when several uncertainties are present about the parameters of the model. Speci cally: on the one hand, we study approximations made on the transition probabilities, the discount factor and the reward functions when the state ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Kybernetika
سال: 2017
ISSN: 0023-5954,1805-949X
DOI: 10.14736/kyb-2017-4-0694