Language-measure-theoretic optimal control of probabilistic finite-state systems.
Ishanu ChattopadhyayAsok RayPublished in: CDC (2007)
Keyphrases
- optimal control
- finite state
- markov chain
- average cost
- feedback control
- dynamic programming
- markov decision processes
- model checking
- class of nonlinear systems
- risk sensitive
- context free
- natural language
- reinforcement learning
- optimal policy
- control problems
- policy iteration
- probabilistic context free grammars
- distance measure
- probabilistic model
- infinite horizon
- np hard
- objective function
- bayesian networks