Adaptive control of Markov processes with incomplete state information and unknown parameters
From MaRDI portal
Publication:1071659
DOI10.1007/BF00941283zbMath0585.90090MaRDI QIDQ1071659
Onésimo Hernández-Lerma, Steven I. Marcus
Publication date: 1987
Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)
approximationsunknown parametersnonstationary value iterationpartially observed Markov decision processesprinciple of estimation and controlasymptotically optimal adaptive policiesdiscounted reward criterionoptimal reward function
Related Items (5)
On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes ⋮ Nonparametric adaptive control of discrete-time partially observable stochastic systems ⋮ Adaptive control of constrained Markov chains: Criteria and policies ⋮ Adaptive control of service in queueing systems ⋮ Optimal cost and policy for a Markovian replacement problem
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Convergence results for continuous-time adaptive stochastic filtering algorithms
- Adaptive control of discounted Markov decision chains
- Analysis of a general recursive prediction error identification algorithm
- Incomplete information in Markovian decision models
- On conditional least squares estimation for stochastic processes
- A Survey of Some Results in Stochastic Adaptive Control
- State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
- SEMI-MARKOV DECISION PROCESSES WITH INCOMPLETE STATE OBSERVATION : AVERAGE COST CRITERION
- Strongly consistent estimation in a controlled Markov renewal model
- Bounds for the regret loss in dynamic programming under adaptive control
- A Markov Quality Control Process Subject to Partial Observation
- Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
- Optimal Inspection and Repair of a Production Process Subject to Deterioration
- SEMI-MARKOV DECISION PROCESSES WITH INCOMPLETE STATE OBSERVATION : DISCOUNTED COST CRITERION
- Estimation and control in Markov chains
- Statistical Inference for Probabilistic Functions of Finite State Markov Chains
- Discrete-Time Markovian Decision Processes with Incomplete State Observation
- A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains
This page was built for publication: Adaptive control of Markov processes with incomplete state information and unknown parameters
