On the embedding of state space realizations.
Yves V. GeninAntoine VandendorpePublished in: Math. Control. Signals Syst. (2007)
Keyphrases
- state space
- reinforcement learning
- heuristic search
- markov chain
- dynamical systems
- random variables
- dynamic programming
- markov decision processes
- state transition
- neural network
- state variables
- optimal policy
- planning problems
- particle filter
- reinforcement learning algorithms
- search space
- nonlinear dimensionality reduction
- goal state
- action space
- database
- initial state
- multi agent
- real time