Limiting discounted-cost control of partially observable stochastic systems.
Onésimo Hernández-LermaRosario RomeraPublished in: CDC (2002)
Keyphrases
- partially observable
- stochastic systems
- infinite horizon
- markov decision processes
- average cost
- optimal control
- sample path
- optimal policy
- dynamical systems
- control system
- state space
- stochastic models
- reinforcement learning
- decision problems
- policy iteration
- confidence intervals
- long run
- finite horizon
- expected cost
- markov chain
- dynamic programming
- control method
- probabilistic model