Observation-based Performance Sensitivity Analysis for POMDPs

被引：0
|
作者：
Ji, Zhe [1 ]
Jiang, Xiaofeng [1 ]
Xi, Hongsheng [1 ]
机构：
[1] Univ Sci & Technol China, Sch Informat Sci & Technol, Dept Auto, Hefei 230027, Peoples R China
来源：
2015 34TH CHINESE CONTROL CONFERENCE (CCC) | 2015年
关键词：
POMDPs; Performance sensitivity analysis; Performance difference formula; Performance derivative formula;
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 this paper, the performance sensitivity analysis for Markov decision processes (MDPs) are generalized to study the partially observable Markov decision processes (POMDPs). The performance derivative formula and the performance difference formula based on observation are derived in this paper. The derivation does not need any overly strict assumptions. In order to find the optimal policy based on observation, an observation-based policy iteration algorithm is designed. An example is presented to show the applicability of the algorithm finally.
引用
收藏
页码：1671 / 1676
页数：6
相关论文
共 50 条
  • [31] A framework for observation-based modelling in model-based testing
    Kanstrén, Teemu
    VTT Publications, 2010, (727): : 1 - 211
  • [32] The effect of camera location on observation-based posture estimation
    Qu, Yan
    Hwang, Jaejin
    Lee, Kyung-Sun
    Jung, Myung-Chul
    ERGONOMICS, 2012, 55 (08) : 885 - 897
  • [33] Observation-Based Trends of the Southern Ocean Carbon Sink
    Ritter, R.
    Landschuetzer, P.
    Gruber, N.
    Fay, A. R.
    Iida, Y.
    Jones, S.
    Nakaoka, S.
    Park, G. -H.
    Peylin, P.
    Roedenbeck, C.
    Rodgers, K. B.
    Shutler, J. D.
    Zeng, J.
    GEOPHYSICAL RESEARCH LETTERS, 2017, 44 (24) : 12339 - 12348
  • [34] Transitive Observation-Based Causation, Saliency, and the Markov Condition
    Bonnefon, Jean-Francois
    Dubois, Didier
    Prade, Henri
    SCALABLE UNCERTAINTY MANAGEMENT, SUM 2008, 2008, 5291 : 78 - +
  • [35] Observation-Based Radiative Kernels From CloudSat/CALIPSO
    Kramer, Ryan J.
    Matus, Alexander V.
    Soden, Brian J.
    L'Ecuyer, Tristan S.
    JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES, 2019, 124 (10) : 5431 - 5444
  • [36] Towards observation-based gridded runoff estimates for Europe
    Gudmundsson, L.
    Seneviratne, S. I.
    HYDROLOGY AND EARTH SYSTEM SCIENCES, 2015, 19 (06) : 2859 - 2879
  • [37] Observation-based learning for brain-machine interfaces
    Tkach, Dennis
    Reimer, Jake
    Hatsopoulos, Nicholas G.
    CURRENT OPINION IN NEUROBIOLOGY, 2008, 18 (06) : 589 - 594
  • [38] Ensemble-based approximation of observation impact using an observation-based verification metric
    Sommer, Matthias
    Weissmann, Martin
    TELLUS SERIES A-DYNAMIC METEOROLOGY AND OCEANOGRAPHY, 2016, 68
  • [39] Observation-Based Multi-Agent Planning with Communication
    Gasparini, Luca
    Norman, Timothy J.
    Kollingbaum, Martin J.
    ECAI 2016: 22ND EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, 285 : 444 - 452
  • [40] PERFORMANCE OF THE OBSERVATION-BASED SOURCE TERMS IN A HIGH-RESOLUTION WAVE HINDCAST FOR THE NORTH SEA
    Rapizo, Henrique
    Liu, Qingxiang
    Babanin, Alexander V.
    PROCEEDINGS OF ASME 2022 41ST INTERNATIONAL CONFERENCE ON OCEAN, OFFSHORE & ARCTIC ENGINEERING, OMAE2022, VOL 2, 2022,
12345