Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
From MaRDI portal
Publication:4507473
DOI10.1137/S0363012998345172zbMath1011.93110OpenAlexW2040434095MaRDI QIDQ4507473
Publication date: 18 October 2000
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1137/s0363012998345172
dynamic programmingpartial observationscontrolled Markov chainsaverage cost controlvanishing discount limit
Filtering in stochastic control theory (93E11) Dynamic programming (90C39) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)
Related Items (15)
Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control ⋮ Finite-Memory Strategies in POMDPs with Long-Run Average Objectives ⋮ Geometry of information structures, strategic measures and associated stochastic control topologies ⋮ Isomorphism Properties of Optimality and Equilibrium Solutions Under Equivalent Information Structure Transformations: Stochastic Dynamic Games and Teams ⋮ Zero-sum games involving teams against teams: existence of equilibria, and comparison and regularity in information ⋮ Sequential stochastic control (single or multi-agent) problems nearly admit change of measures with independent measurement ⋮ Partially observed semi-Markov zero-sum games with average payoff ⋮ A further remark on dynamic programming for partially observed Markov processes ⋮ Weak Feller property of non-linear filters ⋮ On the existence of stationary optimal policies for partially observed MDPs under the long-run average cost criterion ⋮ Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterion ⋮ Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes ⋮ History-dependent Evaluations in Partially Observable Markov Decision Process ⋮ Long Run Control with Degenerate Observation ⋮ Dynamic programming for ergodic control with partial observations.
This page was built for publication: Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
