Value Function Approximation
(Redirected from Neuro-Dynamic Programming)
Jump to navigation
Jump to search
- See: Curse of Dimensionality; Dynamic Programming; Feature Selection; Gaussian Process Reinforcement Learning; Least-Square Reinforcement Learning Methods; Q-Learning: Radial Basis Functions; Reinforcement Learning; Temporal Difference Learning; Value Iteration.
References
2011
- (Lagoudakis, 2011) ⇒ Michail G. Lagoudakis. (2011). “Value Function Approximation.” In: (Sammut & Webb, 2011) p.1011