On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
From MaRDI portal
Publication:2638968
DOI10.1007/BF02283610zbMath0717.90094OpenAlexW2107338824WikidataQ60167566 ScholiaQ60167566MaRDI QIDQ2638968
Emmanuel Fernández-Gaucherand, Aristotle Arapostathis, Steven I. Marcus
Publication date: 1991
Published in: Annals of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/bf02283610
machine replacementpartially observable Markov decision processesuncountable state spaceaverage cost optimal policiesfinite action setdiscount optimal policies
Reliability, availability, maintenance, inspection in operations research (90B25) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)
Related Items (6)
A note on the Ross-Taylor theorem ⋮ On the computation of the optimal cost function for discrete time Markov models with partial observations ⋮ Monotonicity properties for two-action partially observable Markov decision processes on partially ordered spaces ⋮ Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes ⋮ OPTIMAL MIXING OF MARKOV DECISION RULES FOR MDP CONTROL ⋮ Long Run Control with Degenerate Observation
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Adaptive control of Markov processes with incomplete state information and unknown parameters
- An optimal inspection and replacement policy under incomplete state information
- Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains
- Necessary conditions for the optimality equation in average-reward Markov decision processes
- Monotone control laws for noisy, countable-state Markov chains
- Conditions for characterizing the structure of optimal strategies in infinite-horizon dynamic programs
- Optimal control of a partially observable discrete Markov process
- Stochastic optimal control. The discrete time case
- Average cost Markov decision processes under the hypothesis of Doeblin
- Analysis of an identification algorithm arising in the adaptive estimation of Markov chains
- Average cost optimal policies for Markov control processes with Borel state space and unbounded costs
- Optimal control of Markov processes with incomplete state information
- Optimal control of Markov processes with incomplete state-information. II: The convexity of the loss-function
- Markov Decision Processes with a Borel Measurable Cost Function—The Average Case
- Technical Note—On the Convexity of Policy Regions in Partially Observed Systems
- Some Monotonicity Results for Partially Observed Markov Decision Processes
- A Quality Control Model with Learning Effects
- Control of Markov Chains with Long-Run Average Cost Criterion: The Dynamic Programming Equations
- Average Cost Optimal Stationary Policies in Infinite State Markov Decision Processes with Unbounded Costs
- The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
- Structural Results for Partially Observable Markov Decision Processes
- Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic Systems
- State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
- Bounds on optimal cost for a replacement problem with partial observations
- On the Optimality of Structured Policies in Countable Stage Decision Processes
- A Markov Quality Control Process Subject to Partial Observation
- On the Optimality of Structured Policies in Countable Stage Decision Processes. II: Positive and Negative Problems
- Computing optimal quality control policies — two actions
- Optimal Inspection and Repair of a Production Process Subject to Deterioration
- The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
- Optimal replacement policy with unobservable states
- Stationary Markovian Decision Problems and Perturbation Theory of Quasi-Compact Linear Operators
- Optimal control-limit strategies for a partially observed replacement problem†
- The Optimal Control of Partially Observable Markov Processes over a Finite Horizon
- Markovian Sequential Replacement Processes
- Arbitrary State Markovian Decision Processes
- Discrete-Time Markovian Decision Processes with Incomplete State Observation
- Quality Control under Markovian Deterioration
- Markov decision processes
This page was built for publication: On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processes
