Convergence of discretization procedure in Q-learning

Kongzhi Lilun Yu Yingyong/Control Theory and Applications

Volumn 16, Issue 2, 1999, Pages

  Jiang, Guofei ^a   Gao, Huiqi ^a   Wu, Cangpu ^a  

^a BEIJING INSTITUTE OF TECHNOLOGY   (China)

Author keywords

Continuous state and control spaces; Discretization; Dynamic programming; Markovian decision problems; Q Learning

Indexed keywords

EID: 77449144618     PISSN: 10008152     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (5)

1. Watkins C I C H. Learning from delayed rewards. Ph.D. Dissertation, King's College, UK, 1989.
2. Bertseks D P. Convergence of discretization procedure in dynamic programming. IEEE Trans. Automat. Contr., 1975, AC-20:415-419.
3. Whitt W. Approximations of dynamic programs I. Mathematics of Opertion Research, 1978,3:231-243.
4. Chow CS & Tsitsiklis JN. An optimal one-way multigrid algorithm for discrete-time stochastic control. IEEE Trans. Automat. Contr., 1991, AC-36-898-914.
5. Bertseks D P. Stochastic optimal control: the discrete time case. Academic Press, 1978.