scispace - formally typeset
Search or ask a question
Topic

Stochastic game

About: Stochastic game is a research topic. Over the lifetime, 9493 publications have been published within this topic receiving 202664 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: A set of weak conditions guaranteeing both existence and uniqueness of the boundary characterizing the optimal policy and its value are stated, establishing a general ordering for both the values and the marginal values of the considered stochastic control problems.
Abstract: We consider a class of stochastic impulse control problems of linear diffusions arising in studies considering the determination of optimal dividend policies. This class of problems appears also in studies analyzing the optimal management of renewable resources. We state a set of weak conditions guaranteeing both existence and uniqueness of the boundary characterizing the optimal policy and its value. We also analyze two associated stochastic control problems and establish a general ordering for both the values and the marginal values of the considered stochastic control problems. In this way we extend previous findings obtained by relying on linear payoff characterizations.

55 citations

Posted ContentDOI
TL;DR: In this paper, two new empirically sound equilibria, equity-driven impulse balance equilibrium (EIBE) and quantal response equilibrium (QRE), were proposed to provide a psychological reference point to compare the available payoff allocations.
Abstract: Substantial evidence has accumulated in recent empirical works on the limited ability of the Nash equilibrium to rationalize observed behavior in many classes of games played by experimental subjects. This realization has led to several attempts aimed at finding tractable equilibrium concepts which perform better empirically; one such example is the impulse balance equilibrium (Selten, Chmura, 2008), which introduces a psychological reference point to which players compare the available payoff allocations. This paper is concerned with advancing two new, empirically sound, concepts: equity-driven impulse balance equilibrium (EIBE) and equity-driven quantal response equilibrium (EQRE): both introduce a distributive reference point to the corresponding established stationary concepts known as impulse balance equilibrium (IBE) and quantal response equilibrium (QRE). The explanatory power of the considered models leads to the following ranking, starting with the most successful in terms of fit to the experimental data: EQRE, IBE, EIBE, QRE and Nash equilibrium.

55 citations

Journal ArticleDOI
Yan Chen1, Beibei Wang1, W S Lin1, Yongle Wu1, K.J.R. Liu1 
TL;DR: Compared to the traditional non-cooperative P2P schemes, the proposed cooperative scheme achieves much better performance in terms of social welfare, probability of real-time streaming, and video quality (source rate).
Abstract: While peer-to-peer (P2P) video streaming systems have achieved promising results, they introduce a large number of unnecessary traverse links, which consequently leads to substantial network inefficiency. To address this problem and achieve better streaming performance, we propose to enable cooperation among “group peers,” which are geographically neighboring peers with large intra-group upload and download bandwidths. Considering the peers' selfish nature, we formulate the cooperative streaming problem as an evolutionary game and derive, for every peer, the evolutionarily stable strategy (ESS), which is the stable Nash equilibrium and no one will deviate from. Moreover, we propose a simple and distributed learning algorithm for the peers to converge to the ESSs. With the proposed algorithm, each peer decides whether to be an agent who downloads data from the peers outside the group or a free-rider who downloads data from the agents by simply tossing a coin, where the probability of being a head for the coin is learned from the peer's own past payoff history. Simulation results show that the strategy of a peer converges to the ESS. Compared to the traditional non-cooperative P2P schemes, the proposed cooperative scheme achieves much better performance in terms of social welfare, probability of real-time streaming, and video quality (source rate).

55 citations

Book ChapterDOI
23 Feb 2006
TL;DR: In this article, a polynomial time algorithm for the qualitative termination problem of 1-exit RMDPs and 1-leave RSSGs is given. But the problem is in NP∩coNP, and furthermore, it is at least as hard as other well-known NP ∩ coNP problems on games, e.g., Condon's quantitative termination problem for finite SSGs.
Abstract: Recursive Markov Decision Processes (RMDPs) and Recursive Simple Stochastic Games (RSSGs) are natural models for recursive systems involving both probabilistic and non-probabilistic actions. As shown recently [10], fundamental problems about such models, e.g., termination, are undecidable in general, but decidable for the important class of 1-exit RMDPs and RSSGs. These capture controlled and game versions of multi-type Branching Processes, an important and well-studied class of stochastic processes. In this paper we provide efficient algorithms for the qualitative termination problem for these models: does the process terminate almost surely when the players use their optimal strategies? Polynomial time algorithms are given for both maximizing and minimizing 1-exit RMDPs (the two cases are not symmetric). For 1-exit RSSGs the problem is in NP∩coNP, and furthermore, it is at least as hard as other well-known NP∩coNP problems on games, e.g., Condon's quantitative termination problem for finite SSGs ([3]). For the class of linearly-recursive 1-exit RSSGs, we show that the problem can be solved in polynomial time.

55 citations

Journal ArticleDOI
TL;DR: In this article, a new axiomatization of the Shapley is presented, and an associated game is constructed, where the term of order n, in this sequence, is the associated game of the term n−1.
Abstract: In this work, a new axiomatization of the Shapley is presented. An associated game is constructed. We define a sequence of games, when the term of order n, in this sequence, is the associated game of the term of order (n−1). We show that the sequence converges and that the limit game is inessential. The solution is obtained using the inessential game axiom, the associated consistency axiom and the continuity axiom. As a by-product, we note that neither the additivity nor the efficiency axioms are needed.

55 citations


Network Information
Related Topics (5)
Markov chain
51.9K papers, 1.3M citations
81% related
Incentive
41.5K papers, 1M citations
81% related
Heuristics
32.1K papers, 956.5K citations
80% related
Linear programming
32.1K papers, 920.3K citations
79% related
Empirical research
51.3K papers, 1.9M citations
78% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
2023364
2022738
2021462
2020512
2019460
2018483