Average cost dynamic programming equations for controlled Markov chains with partial observations

SIAM Journal on Control and Optimization

Volumn 39, Issue 3, 2000, Pages 673-681

  Borkar, V S ^a  

^a TATA INSTITUTE OF FUNDAMENTAL RESEARCH   (India)

Author keywords

Average cost control; Controlled Markov chains; Dynamic programming; Partial observations; Vanishing discount limit

Indexed keywords

BOUNDARY CONDITIONS; CONTROLLABILITY; CONVERGENCE OF NUMERICAL METHODS; COST BENEFIT ANALYSIS; FUNCTION EVALUATION; MARKOV PROCESSES; NONLINEAR FILTERING; OBSERVABILITY; PROBABILITY DISTRIBUTIONS; STATE SPACE METHODS;

AVERAGE COST CONTROL; PARTIAL OBSERVATIONS; VANISHING DISCOUNT LIMIT; WIDE SENSE ADMISSBLE CONTROL;

DYNAMIC PROGRAMMING;

EID: 0034437507     PISSN: 03630129     EISSN: None     Source Type: Journal    
DOI: 10.1137/S0363012998345172     Document Type: Article

References (12)

1. Discrete-time controlled Markov processes with average cost criterion: A survey
2. White-noise representations in stochastic realization theory
3. Topics in controlled Markov chains
4. On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
5. Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes
6. Optimal control of partially observed diffusions
7. Optimal infinite-horizon undiscounted control of finite probabilistic systems
8. Approximations of discrete time partially observed control problems
9. Ergodic control of partially observed Markov processes with equivalent transition probabilities
10. Survey of measurable selection theorems