Discretization procedures for adaptive Markov control processes
From MaRDI portal
Publication:1123872
DOI10.1016/0022-247X(89)90259-XzbMath0677.93073MaRDI QIDQ1123872
Steven I. Marcus, Onésimo Hernández-Lerma
Publication date: 1989
Published in: Journal of Mathematical Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0022-247x(89)90259-x
infinite horizon; parameter estimation; discrete-time; asymptotically optimal; uniform approximations; adaptive Markov control processes; unknown disturbance distribution
60J05: Discrete-time Markov processes on general state spaces
93C40: Adaptive control/observation systems
Related Items
A perturbation approach to approximate value iteration for average cost Markov decision processes with Borel spaces and bounded costs, A convex optimization approach to dynamic programming in continuous state and action spaces, Value iteration in average cost Markov control processes on Borel spaces, Note on stability estimation in average Markov control processes
Cites Work
- Adaptive control of discounted Markov decision chains
- Adaptive policies for discrete-time stochastic control systems with unknown disturbance distribution
- Continuous dependence of stochastic control models on the noise distribution
- Nonstationary Markov decision problems with converging parameters
- Stochastic optimal control. The discrete time case
- Empirical processes: A survey of results for independent and identically distributed random variables
- Approximation and bounds in discrete event dynamic programming
- Estimation and control in discounted stochastic dynamic programming
- Strongly consistent estimation in a controlled Markov renewal model
- Convergence of Dynamic Programming Models
- Convergence of discretization procedures in dynamic programming
- Optimal Plans for Dynamic Programming Problems
- Approximations of Dynamic Programs, I
- Approximations of Dynamic Programs, II
- An Approach to Discrete-Time Stochastic Control Problems under Partial Observation
- Estimation and control in Markov chains
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item