Choice of state-space basis in combined deterministic-stochastic subspace identification.
Peter Van OverscheeBart De MoorPublished in: Autom. (1995)
Keyphrases
- state space
- stochastic domains
- finite state automaton
- reinforcement learning
- fully observable
- stochastic methods
- low dimensional
- dynamical systems
- stochastic optimization problems
- continuous state spaces
- state transition
- particle filter
- principal component analysis
- heuristic search
- markov decision processes
- dynamic programming
- search space
- optimal policy
- markov chain
- feature space
- principal components
- state variables
- high dimensional
- stochastic model
- learning automata
- stochastic optimization
- feature extraction
- lower bound
- linear subspace
- planning problems
- feature selection
- monte carlo