國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Zero-sum discrete-time Markov games ...

Minjarez-Sosa, J. Adolfo.

Zero-sum discrete-time Markov games with unknown disturbance distributiondiscounted and average criteria /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Zero-sum discrete-time Markov games with unknown disturbance distributionby J. Adolfo Minjarez-Sosa.
其他題名:	discounted and average criteria /
作者:	Minjarez-Sosa, J. Adolfo.
出版者:	Cham :Springer International Publishing :2020.
面頁冊數:	xiv, 120 p. :ill., digital ;24 cm.
Contained By:	Springer eBooks
標題:	Markov processes.
電子資源:	https://doi.org/10.1007/978-3-030-35720-7
ISBN:	9783030357207$q(electronic bk.)

Zero-sum discrete-time Markov games with unknown disturbance distributiondiscounted and average criteria /
Minjarez-Sosa, J. Adolfo.

Zero-sum discrete-time Markov games with unknown disturbance distributiondiscounted and average criteria /[electronic resource] :by J. Adolfo Minjarez-Sosa. - Cham :Springer International Publishing :2020. - xiv, 120 p. :ill., digital ;24 cm. - SpringerBriefs in probability and mathematical statistics,2365-4333. - SpringerBriefs in probability and mathematical statistics..

Zero-sum Markov games -- Discounted optimality criterion -- Average payoff criterion -- Empirical approximation-estimation algorithms in Markov games -- Difference-equation games: examples -- Elements from analysis -- Probability measures and weak convergence -- Stochastic kernels -- Review on density estimation.

This SpringerBrief deals with a class of discrete-time zero-sum Markov games with Borel state and action spaces, and possibly unbounded payoffs, under discounted and average criteria, whose state process evolves according to a stochastic difference equation. The corresponding disturbance process is an observable sequence of independent and identically distributed random variables with unknown distribution for both players. Unlike the standard case, the game is played over an infinite horizon evolving as follows. At each stage, once the players have observed the state of the game, and before choosing the actions, players 1 and 2 implement a statistical estimation process to obtain estimates of the unknown distribution. Then, independently, the players adapt their decisions to such estimators to select their actions and construct their strategies. This book presents a systematic analysis on recent developments in this kind of games. Specifically, the theoretical foundations on the procedures combining statistical estimation and control techniques for the construction of strategies of the players are introduced, with illustrative examples. In this sense, the book is an essential reference for theoretical and applied researchers in the fields of stochastic control and game theory, and their applications.

ISBN: 9783030357207$q(electronic bk.)

Standard No.: 10.1007/978-3-030-35720-7doiSubjects--Topical Terms:

181910
Markov processes.

LC Class. No.: QA274.7 / .M565 2020

Dewey Class. No.: 519.233

Zero-sum discrete-time Markov games with unknown disturbance distributiondiscounted and average criteria /
LDR:02785nmm a2200349 a 4500 001 573682
003 DE-He213
005 20200624142702.0
006 m d
007 cr nn 008maaau
008 200928s2020 sz s 0 eng d
020 $a 9783030357207$q(electronic bk.)
020 $a 9783030357191$q(paper)
024 7 $a 10.1007/978-3-030-35720-7 $2 doi
035 $a 978-3-030-35720-7
040 $a GP $c GP
041 0 $a eng
050 4 $a QA274.7 $b .M565 2020
072 7 $a PBT $2 bicssc
072 7 $a MAT029000 $2 bisacsh
072 7 $a PBT $2 thema
072 7 $a PBWL $2 thema
082 0 4 $a 519.233 $2 23
090 $a QA274.7 $b .M665 2020
100 1 $a Minjarez-Sosa, J. Adolfo. $3 573102
245 1 0 $a Zero-sum discrete-time Markov games with unknown disturbance distribution $h [electronic resource] : $b discounted and average criteria / $c by J. Adolfo Minjarez-Sosa.
260 $a Cham : $b Springer International Publishing : $b Imprint: Springer, $c 2020.
300 $a xiv, 120 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in probability and mathematical statistics, $x 2365-4333
505 0 $a Zero-sum Markov games -- Discounted optimality criterion -- Average payoff criterion -- Empirical approximation-estimation algorithms in Markov games -- Difference-equation games: examples -- Elements from analysis -- Probability measures and weak convergence -- Stochastic kernels -- Review on density estimation.
520 $a This SpringerBrief deals with a class of discrete-time zero-sum Markov games with Borel state and action spaces, and possibly unbounded payoffs, under discounted and average criteria, whose state process evolves according to a stochastic difference equation. The corresponding disturbance process is an observable sequence of independent and identically distributed random variables with unknown distribution for both players. Unlike the standard case, the game is played over an infinite horizon evolving as follows. At each stage, once the players have observed the state of the game, and before choosing the actions, players 1 and 2 implement a statistical estimation process to obtain estimates of the unknown distribution. Then, independently, the players adapt their decisions to such estimators to select their actions and construct their strategies. This book presents a systematic analysis on recent developments in this kind of games. Specifically, the theoretical foundations on the procedures combining statistical estimation and control techniques for the construction of strategies of the players are introduced, with illustrative examples. In this sense, the book is an essential reference for theoretical and applied researchers in the fields of stochastic control and game theory, and their applications.
650 0 $a Markov processes. $3 181910
650 0 $a Differential games. $3 190628
650 1 4 $a Probability Theory and Stochastic Processes. $3 274061
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer eBooks
830 0 $a SpringerBriefs in probability and mathematical statistics. $3 732767
856 4 0 $u https://doi.org/10.1007/978-3-030-35720-7
950 $a Mathematics and Statistics (Springer-11649)