Mean, variance and probabilistic criteria in finite Markov decision processes: A review
From MaRDI portal
Publication:1821706
DOI10.1007/BF00938524zbMath0616.90096MaRDI QIDQ1821706
Publication date: 1988
Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)
surveymeanvariancefinite-horizonprobabilistic criteriadiscounted formulationsinfinite-horizon nondiscounted formulationsnonstandard Markov decision process criteria
Related Items
Risk measurement and risk-averse control of partially observable discrete-time Markov systems, Optimal models for the first arrival time distribution function in continuous time -- with a special case, Experiments with dynamic programming algorithms for nonseparable problems, Reliability of internal prediction/estimation and its application. I: Adaptive action selection reflecting reliability of value function, Analyzing operational risk-reward trade-offs for start-ups, Markov Decision Problems Where Means Bound Variances, Non-homogeneous Markov decision processes with a constraint, Survey of linear programming for standard and nonstandard Markovian control problems. Part I: Theory, Discounting axioms imply risk neutrality, Variance minimization for constrained discounted continuous-time MDPs with exponentially distributed stopping times, Markov decision processes with average-value-at-risk criteria, Unnamed Item, Threshold probability of non-terminal type in finite horizon Markov decision processes, Optimal control by random sequences with constraints, Markov decision processes, Risk-Constrained Reinforcement Learning with Percentile Risk Criteria, On the total reward variance for continuous-time Markov reward chains, A Sensitivity‐Based Construction Approach to Variance Minimization of Markov Decision Processes, Optimization models for the first arrival target distribution function in discrete time, A note on maximal mean/standard deviation ratio in an undiscounted MDP, An Inequality for Variances of the Discounted Rewards, Minimizing risk models in Markov decision processes with policies depending on target values, Optimal policy for minimizing risk models in Markov decision processes, Mean-variance criteria in an undiscounted Markov decision process, On mean reward variance in semi-Markov processes, Computational Methods for Risk-Averse Undiscounted Transient Markov Models, Process-based risk measures and risk-averse control of discrete-time systems, Notes on average Markov decision processes with a minimum-variance criterion
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Percentiles and Markovian decision processes
- A systematic approach to determining mean-variance tradeoffs when managing randomly varying populations
- Proper efficiency with respect to cones
- Stable sequential control rules and Markov chains
- Finite state Markovian decision processes
- Chance-Constrained Programming
- A Preference Order Dynamic Program for a Knapsack Problem with Stochastic Rewards
- The Decomposition Algorithm for Linear Programs
- Multiplicative Markov Decision Chains
- Constrained Undiscounted Stochastic Dynamic Programming
- Preference Order Stochastic Knapsack Problems: Methodological Issues
- Ordinal Dynamic Programming
- On the Optimality of Structured Policies in Countable Stage Decision Processes
- A Utility Criterion for Markov Decision Processes
- Dynamic Programming for a Stochastic Markovian Process with an Application to the Mean Variance Models
- Decision Problems with Expected Utility Critera, I: Upper and Lower Convergent Utility
- Decision Problems with Expected Utility Criteria, II: Stationarity
- The variance of discounted Markov decision processes
- A Class of Variance-Constrained Problems
- Technical Note—Dynamic Programming and Probabilistic Constraints
- Some Remarks on Finite Horizon Markovian Decision Models
- A Note on Memoryless Rules for Controlling Sequential Control Processes
- On Sequential Control Processes
- Chance Constraints and Normal Deviates
- Dynamic Programming with Linear Uncertainty
- Probability Bounds in Replacement Policies for Markov Systems
- Risk-Sensitive Markov Decision Processes
- Constrained Markov Decision Chains
