JEmpirical Dynamic Programming for Controlled Diffusion Processes

被引:0
|
作者
Karumanchi, Sambhu H. [1 ]
Belabbas, Mohamed A. [2 ]
Hovakimyan, Naira [3 ]
机构
[1] Univ Illinois, Dept Aerosp Engn, Urbana, IL 61801 USA
[2] Univ Illinois, Dept Elect & Comp Engn, Urbana, IL USA
[3] Univ Illinois, Dept Mech Sci & Engn, Urbana, IL USA
来源
IFAC PAPERSONLINE | 2023年 / 56卷 / 02期
基金
美国国家科学基金会;
关键词
Stochastic optimal control; Numerical methods for optimal control; Diffusion; processes; Reinforcement learning; Markov decision process; Value iteration; ALGORITHM;
D O I
10.1016/j.ifacol.2023.10.854
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We consider Markov chain approximation for optimal control of diffusion processes under infinite horizon discounted cost optimality and apply the simulation-based Empirical Value Iteration to estimate the value function of each approximating chain. We follow a nested multi-grid discretization of the state space to establish weak convergence of the value function sequence to the value function of the original controlled diffusion. We illustrate the convergence performance of the model on the popular Benes' bang-bang control problem [Bene.s (1974)].
引用
收藏
页码:11235 / 11241
页数:7
相关论文
共 50 条
  • [31] CONTROLS OPTIMAL FROM TIME T ONWARD AND DYNAMIC-PROGRAMMING FOR SYSTEMS OF CONTROLLED JUMP PROCESSES
    RISHEL, R
    MATHEMATICAL PROGRAMMING STUDY, 1976, 6 (DEC): : 125 - 153
  • [32] DYNAMIC-PROGRAMMING PRINCIPLE FOR CONTROLLED TREES
    MAZLIAK, L
    COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE I-MATHEMATIQUE, 1992, 314 (07): : 563 - 566
  • [33] Dynamic Programming of a DNA Walker Controlled by Protons
    Yao, Dongbao
    Bhadra, Sanchita
    Erhu, Xiong
    Liang, Haojun
    Ellington, Andrew D.
    Jung, Cheulhee
    ACS NANO, 2020, 14 (04) : 4007 - 4013
  • [34] Technical stability of controlled dynamic processes
    Matviichuk, K.S.
    Chemical Week, 1999, 161 (11): : 754 - 759
  • [35] Technical stability of controlled dynamic processes
    Matviichuk, KS
    INTERNATIONAL APPLIED MECHANICS, 1997, 33 (09) : 754 - 759
  • [36] Unique programming techniques dedicated for software controlled processes
    Klaudiusz, M
    Andrzej, N
    Wojciech, O
    Zygmunt, M
    PROGRAMMABLE DEVICES AND SYSTEMS 2001, 2002, : 151 - 156
  • [37] Technical stability of controlled dynamic processes
    K. S. Matviichuk
    International Applied Mechanics, 1997, 33 : 754 - 759
  • [38] USE OF CONTROLLED PROGRAMMING PROCESSES FOR THE PRODUCTION OF FRUIT PULP
    HURLER, KA
    INDUSTRIE ALIMENTARI, 1983, 22 (09): : 668 - 669
  • [39] KINETICS OF DIFFUSION-CONTROLLED PROCESSES ON FRACTALS
    MOSOLOV, AB
    ZHURNAL EKSPERIMENTALNOI I TEORETICHESKOI FIZIKI, 1991, 99 (01): : 295 - 299
  • [40] Characterizations of overtaking optimality for controlled diffusion processes
    Jasso-Fuentes, Hector
    Hernandez-Lerma, Onesimo
    APPLIED MATHEMATICS AND OPTIMIZATION, 2008, 57 (03): : 349 - 369