2-D state-space realizations with fewer multipliers and invariant norms.
Tyseer AboulnasrMoustafa M. FahmyPublished in: ICASSP (1983)
Keyphrases
- state space
- heuristic search
- markov decision processes
- reinforcement learning
- markov chain
- affine transformation
- dynamic programming
- dynamical systems
- particle filter
- state variables
- reinforcement learning algorithms
- continuous time markov process
- moment invariants
- state transition
- markov decision process
- translation invariant
- stochastic domains
- invariant features
- optimal policy
- multi agent systems
- database
- markovian decision
- finite state automaton
- invariant properties
- random variables
- probabilistic model
- object recognition
- neural network