Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterion
From MaRDI portal
Publication:3368567
DOI10.1080/17442500500428833zbMath1101.93083OpenAlexW2043032300MaRDI QIDQ3368567
Rolando Cavazos-Cadena, Daniel Hernández-Hernández
Publication date: 31 January 2006
Published in: Stochastics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/17442500500428833
Lipschitz normSchweitzer's transformationBirkhoff's distanceequicontinuity of the value iteration functionsreduction to a completely observable model
Related Items (2)
A central limit theorem for normalized products of random matrices ⋮ Risk-sensitivity vanishing limit for controlled Markov processes
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A pause control approach to the value iteration scheme in average Markov decision processes
- A note on the convergence rate of the value iteration scheme in controlled Markov chains
- Adaptive Markov control processes
- Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management
- Non-negative matrices and Markov chains.
- Optimal control of Markov processes with incomplete state information
- Iterative solution of the functional equations of undiscounted Markov renewal programming
- The vanishing discount approach in Markov chains with risk-sensitive criteria
- State of the Art—A Survey of Partially Observable Markov Decision Processes: Theory, Models, and Algorithms
- Small Parameter Limit for Discrete-Time Partially Observed Risk-Sensitive Control Problems
- Risk-Sensitive Control of Finite State Machines on an Infinite Horizon II
- Risk-sensitive control and dynamic games for partially observed discrete-time nonlinear systems
- Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games
- Small parameter limit for ergodic, discrete-time, partially observed, risk-sensitive control problems
This page was built for publication: Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterion
