Dynamic programming for ergodic control with partial observations.

DOI10.1016/S0304-4149(02)00190-4zbMath1075.60522MaRDI QIDQ2574544

Vivek S. Borkar

Publication date: 29 November 2005

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

zbMATH Keywords

Markov processergodic cost

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Dynamic programming in optimal control and differential games (49L20) Dynamic programming (90C39) Signal detection and filtering (aspects of stochastic processes) (60G35) Optimal stochastic control (93E20)

Related Items (9)

Robustness to Incorrect Priors and Controlled Filter Stability in Partially Observed Stochastic Control ⋮ Geometry of information structures, strategic measures and associated stochastic control topologies ⋮ Ergodic and adaptive control of hidden Markov models ⋮ Partially observed semi-Markov zero-sum games with average payoff ⋮ Zero-sum stochastic games with partial information and average payoff ⋮ Discrete-Time Semi-Markov Random Evolutions and their Applications ⋮ A further remark on dynamic programming for partially observed Markov processes ⋮ Exit time and invariant measure asymptotics for small noise constrained diffusions ⋮ 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
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Markov chains and stochastic stability
• Martingale conditions for the optimal control of continuous time stochastic systems
• Mimicking the one-dimensional marginal distributions of processes having an Ito differential
• Occupation measures for controlled Markov processes: Characterization and optimality
• White-Noise Representations in Stochastic Realization Theory
• A remark on the attainable distributions of controlled diffusions
• Optimal Control for Partially Observed Diffusions
• A splitting technique for Harris recurrent Markov chains
• A New Approach to the Limit Theory of Recurrent Markov Chains
• Survey of Measurable Selection Theorems
• Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
• The value function in ergodic control of diffusion processes with partial observations II
• The value function in ergodic control of diffusion processes with partial observations
• Bounds for the fundamental solution of a parabolic equation
• Necessary and Sufficient Dynamic Programming Conditions for Continuous Time Stochastic Optimal Control
• Dynamic Programming Conditions for Partially Observable Stochastic Systems

This page was built for publication: Dynamic programming for ergodic control with partial observations.