A further remark on dynamic programming for partially observed Markov processes
From MaRDI portal
Publication:2485767
DOI10.1016/j.spa.2004.01.011zbMath1114.93098MaRDI QIDQ2485767
Vivek S. Borkar, Amarjit Budhiraja
Publication date: 5 August 2005
Published in: Stochastic Processes and their Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.spa.2004.01.011
Dynamic programming; Partial observations; Ergodic cost; Controlled Markov processes; Pseudo-atom; Vanishing discount
49L20: Dynamic programming in optimal control and differential games
93E20: Optimal stochastic control
Related Items
Partially observed semi-Markov zero-sum games with average payoff, Ergodic and adaptive control of hidden Markov models, Ergodicity of filtering process by vanishing discount approach, On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Markov chains and stochastic stability
- Remarks on the existence of solutions to the average cost optimality equation in Markov decision processes
- Dynamic programming for ergodic control with partial observations.
- White-Noise Representations in Stochastic Realization Theory
- Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic Systems
- Optimal Control for Partially Observed Diffusions
- Survey of Measurable Selection Theorems
- Ergodic control of partially observed Markov processes with equivalent transition probabilities
- Subgeometric Rates of Convergence of f-Ergodic Markov Chains
- Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations