Markov decision processes with a minimum-variance criterion
From MaRDI portal
The paper considers the optimization of the variance of the sum of costs as well as that of an average expected cost in Markov decision processes with unbounded cost. In case of general state and action space, the stationary policy which makes the average variances as small as possible in the class of policies which are \(\epsilon\)-optimal in an average expected cost is found.
Recommendations
- scientific article; zbMATH DE number 1062627
- Markov Decision Processes with Variance Minimization: A New Condition and Approach
- Notes on average Markov decision processes with a minimum-variance criterion
- Optimization of Markov decision processes under the variance criterion
- Mean-variance criteria in an undiscounted Markov decision process
Cites work
- Alternative Theoretical Frameworks for Finite Horizon Discrete-Time Stochastic Optimal Control
- Denumerable state semi-Markov decision processes with unbounded costs, average cost criterion
- Discounted semi-Markov decision processes: linear programming and policy iteration
- Discrete Dynamic Programming with Sensitive Discount Optimality Criteria
- Estimation and control in Markov chains
- scientific article; zbMATH DE number 3176450 (Why is no real title available?)
- scientific article; zbMATH DE number 3445938 (Why is no real title available?)
- scientific article; zbMATH DE number 3341749 (Why is no real title available?)
- scientific article; zbMATH DE number 3085434 (Why is no real title available?)
- Markov Decision Processes with a Borel Measurable Cost Function—The Average Case
- Markov decision processes with a new optimality criterion: Discrete time
- Semi-Markov decision processes with a reachable state-subset
- Stochastic optimal control. The discrete time case
- The variance of discounted Markov decision processes
Cited in
(28)- A variance minimization problem for a Markov decision process
- Solving Markovian decision processes by successive elimination of variables
- Mean-variance criteria in an undiscounted Markov decision process
- Notes on average Markov decision processes with a minimum-variance criterion
- Variance minimization of parameterized Markov decision processes
- Semi-Markov decision processes with variance minimization criterion
- Bias optimality and strong n (n= -1,0) discount optimality for Markov decision processes
- Optimization of Markov decision processes under the variance criterion
- Sample-path optimality and variance-maximization for Markov decision processes
- STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS*
- First passage optimality and variance minimisation of Markov decision processes with varying discount factors
- Variance-minimization of Markov control processes with pathwise constraints
- Markov Decision Processes with Variance Minimization: A New Condition and Approach
- VARIANCE CONSTRAINED MARKOV DECISION PROCESS
- scientific article; zbMATH DE number 4037634 (Why is no real title available?)
- On the General Utility of Discounted Markov Decision Processes
- Notes on variance in randomized reward Markov decision processes
- scientific article; zbMATH DE number 1062627 (Why is no real title available?)
- Sample-Path Optimality and Variance-Minimization of Average Cost Markov Control Processes
- Mean-Variance Criteria for Finite Continuous-Time Markov Decision Processes
- Controlled Markov decision processes with AVaR criteria for unbounded costs
- Optimal ergodic control of Markov diffusion processes with minimum variance
- On the total reward variance for continuous-time Markov reward chains
- Discrete-time nonstationary average stochastic games
- Variance minimization for continuous-time Markov decision processes: two approaches
- Min-problem for Markov moments and the speed of response
- On mean reward variance in semi-Markov processes
- Mean-variance problems for finite horizon semi-Markov decision processes
This page was built for publication: Markov decision processes with a minimum-variance criterion
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1090254)
