Adjoint Polynomial Formulas for Nonlinear State-Space Realization.
Juri BelikovÜlle KottaMaris TonsoPublished in: IEEE Trans. Autom. Control. (2014)
Keyphrases
- state space
- reinforcement learning
- heuristic search
- state variables
- dynamic programming
- optimal control
- dynamical systems
- search space
- particle filter
- optimal policy
- nonlinear models
- reinforcement learning algorithms
- initial state
- continuous time markov process
- low order
- high order
- basis functions
- belief state
- action space