Error bounds for stochastic shortest path problems

被引：0
|
作者：
Hansen, Eric A. [1 ]
机构：
[1] Mississippi State Univ, Dept Comp Sci & Engn, Mississippi State, MS 39762 USA
来源：
MATHEMATICAL METHODS OF OPERATIONS RESEARCH | 2017年 / 86卷 / 01期
关键词：
Markov decision process; Dynamic programming; HEURISTIC-SEARCH ALGORITHMS;
D O I：
10.1007/s00186-017-0581-5
中图分类号：
C93 [管理学]; O22 [运筹学];
学科分类号：
070105 ; 12 ; 1201 ; 1202 ; 120202 ;
摘要：
For stochastic shortest path problems, error bounds for value iteration due to Bertsekas elegantly generalize the classic MacQueen-Porteus error bounds for discounted infinite-horizon Markov decision problems, but incur prohibitive computational overhead. We derive bounds on these error bounds that can be computed with little or no overhead, making them useful in practice-especially so, since easily-computed error bounds have not previously been available for this class of problems.
引用
收藏
页码：1 / 27
页数：27
相关论文
共 50 条
  • [1] Error bounds for stochastic shortest path problems
    Eric A. Hansen
    Mathematical Methods of Operations Research, 2017, 86 : 1 - 27
  • [2] General Error Bounds in Heuristic Search Algorithms for Stochastic Shortest Path Problems
    Hansen, Eric A.
    Abdoulahi, Ibrahim
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 3130 - 3137
  • [3] Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation
    Vial, Daniel
    Parulekar, Advait
    Shakkottai, Sanjay
    Srikant, R.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [4] Efficient Bounds in Heuristic Search Algorithms for Stochastic Shortest Path Problems
    Hansen, Eric A.
    Abdoulahi, Ibrahim
    PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 3283 - 3290
  • [5] Stochastic shortest path problems with recourse
    Polychronopoulos, GH
    Tsitsiklis, JN
    NETWORKS, 1996, 27 (02) : 133 - 143
  • [6] On partially observed Stochastic shortest path problems
    Patek, SD
    PROCEEDINGS OF THE 40TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 2001, : 5050 - 5055
  • [7] AN ANALYSIS OF STOCHASTIC SHORTEST-PATH PROBLEMS
    BERTSEKAS, DP
    TSITSIKLIS, JN
    MATHEMATICS OF OPERATIONS RESEARCH, 1991, 16 (03) : 580 - 595
  • [8] Soft Labeling in Stochastic Shortest Path Problems
    Pineda, Luis
    Zilberstein, Shlomo
    AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 467 - 475
  • [9] Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
    Tarbouriech, Jean
    Pirotta, Matteo
    Valko, Michal
    Lazaric, Alessandro
    ALGORITHMIC LEARNING THEORY, VOL 132, 2021, 132
  • [10] Minimizing risk models in stochastic shortest path problems
    Yoshio Ohtsubo
    Mathematical Methods of Operations Research, 2003, 57 : 79 - 88
12345