Improving strategies in stochastic games

被引:0
|
作者
Flesch, J [1 ]
Thuijsman, F [1 ]
Vrieze, OJ [1 ]
机构
[1] Maastricht Univ, Dept Math, NL-6200 MD Maastricht, Netherlands
来源
PROCEEDINGS OF THE 37TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4 | 1998年
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In a zero-sum limiting average stochastic game, we evaluate a strategy pi for the maximizing player, player 1, by the reward phi(s)(pi) that pi guarantees to him when starting in state s. A strategy pi is called non-improving if phi(s)(pi) greater than or equal to phi(s)(pi[h]) for any state s and for any finite history h, where pi[h] is the strategy pi conditional on the history h; otherwise the strategy is called improving. We investigate the use of improving and non-improving strategies, and explore the relation between (non-)improvingness and (epsilon-)optimality. Improving strategies appear to play a very important role for obtaining E-optimality, while 0-optimal strategies are always non-improving. Several examples will clarify all these issues.
引用
收藏
页码:2674 / 2679
页数:6
相关论文
共 50 条
  • [21] Evolution of state-dependent strategies in stochastic games
    Wang, Guocheng
    Su, Qi
    Wang, Long
    JOURNAL OF THEORETICAL BIOLOGY, 2021, 527
  • [22] BASIC OPTIMAL STRATEGIES IN STOCHASTIC DIFFERENTIAL-GAMES
    GAIDOV, SD
    DOKLADI NA BOLGARSKATA AKADEMIYA NA NAUKITE, 1984, 37 (04): : 457 - 460
  • [23] Optimal Strategies in Infinite-state Stochastic Reachability Games
    Brozek, Vaclav
    ELECTRONIC PROCEEDINGS IN THEORETICAL COMPUTER SCIENCE, 2011, (54): : 60 - 73
  • [24] Total reward stochastic games and sensitive average reward strategies
    Thuijsman, F
    Vrieze, OJ
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 1998, 98 (01) : 175 - 196
  • [25] Total Reward Stochastic Games and Sensitive Average Reward Strategies
    F. Thuijsman
    O. J. Vrieze
    Journal of Optimization Theory and Applications, 1998, 98 : 175 - 196
  • [26] Determining the Optimal Strategies for Stochastic Positional Games with Discounted Payoffs
    Lozovanu, Dmitrii
    2015 20TH INTERNATIONAL CONFERENCE ON CONTROL SYSTEMS AND COMPUTER SCIENCE, 2015, : 393 - 396
  • [27] Pure Equilibrium Strategies for Stochastic Games via Potential Functions
    Potters, Jos A. M.
    Raghavan, T. E. S.
    Tijs, Stef H.
    ADVANCES IN DYNAMIC GAMES AND THEIR APPLICATIONS: ANALYTICAL AND NUMERICAL DEVELOPMENTS, 2009, 10 : 433 - +
  • [28] Finding Optimal Strategies of Almost Acyclic Simple Stochastic Games
    Auger, David
    Coucheney, Pierre
    Strozecki, Yann
    THEORY AND APPLICATIONS OF MODELS OF COMPUTATION (TAMC 2014), 2014, 8402 : 67 - 85
  • [29] Surprising strategies obtained by stochastic optimization in partially observable games
    Cauwet, Marie-Liesse
    Teytaud, Olivier
    2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2018, : 31 - 38
  • [30] UNIVERSALLY MEASURABLE STRATEGIES IN ZERO-SUM STOCHASTIC GAMES
    NOWAK, AS
    ANNALS OF PROBABILITY, 1985, 13 (01): : 269 - 287