Approximate dynamic programming via linear programming

被引:0
|
作者
de Farias, DP [1 ]
Van Roy, B [1 ]
机构
[1] Stanford Univ, Dept Management Sci & Engn, Stanford, CA 94305 USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The curse of dimensionality gives rise to prohibitive computational requirements that render infeasible the exact solution of large-scale stochastic control problems. We study an efficient method based on linear programming for approximating solutions to such problems. The approach "fits" a linear combination of pre-selected basis functions to the dynamic programming cost-to-go function. We develop bounds on the approximation error and present experimental results in the domain of queueing network control, providing empirical support for the methodology.
引用
收藏
页码:689 / 695
页数:7
相关论文
共 50 条
  • [21] Constrained Bayesian Reinforcement Learning via Approximate Linear Programming
    Lee, Jongmin
    Jang, Youngsoo
    Poupart, Pascal
    Kim, Kee-Eung
    PROCEEDINGS OF THE TWENTY-SIXTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2088 - 2095
  • [22] Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation
    Chakrabarty, Ankush
    Jha, Devesh K.
    Buzzard, Gregery T.
    Wang, Yebin
    Vamvoudakis, Kyriakos G.
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (01) : 405 - 419
  • [23] Single Agent Indirect Herding via Approximate Dynamic Programming
    Deptula, Patryk
    Bell, Zachary I.
    Zegers, Federico M.
    Licitra, Ryan A.
    Dixon, Warren E.
    2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 7136 - 7141
  • [24] Mitigation of Coincident Peak Charges via Approximate Dynamic Programming
    Dowling, Chase P.
    Zhang, Baosen
    2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 4202 - 4207
  • [25] Adaptive Optimal Observer Design via Approximate Dynamic Programming
    Na, Jing
    Herrmann, Guido
    Vamvoudakis, Kyriakos G.
    2017 AMERICAN CONTROL CONFERENCE (ACC), 2017, : 3288 - 3293
  • [26] Model-free approximate dynamic programming schemes for linear systems
    Al-Tamimi, Asma
    Vrabie, Draguna
    Abu-Khalaf, Murad
    Lewis, Frank L.
    2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 371 - +
  • [27] AN APPROXIMATE ALGORITHM FOR DISCRETE LINEAR PROGRAMMING
    BIONDI, E
    SCHMID, R
    IEEE TRANSACTIONS ON SYSTEMS SCIENCE AND CYBERNETICS, 1969, SSC5 (01): : 65 - &
  • [28] An algorithm for approximate multiparametric linear programming
    Filippi, C
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2004, 120 (01) : 73 - 95
  • [29] AN APPROXIMATE METHOD OF INTEGER LINEAR PROGRAMMING
    FINKELSHTEYN, YY
    ENGINEERING CYBERNETICS, 1968, (01): : 36 - +
  • [30] A NOTE ON APPROXIMATE LINEAR-PROGRAMMING
    MEGIDDO, N
    INFORMATION PROCESSING LETTERS, 1992, 42 (01) : 53 - 53