Handbook of Learning and Approximate Dynamic ProgrammingJennie Si
|
From inside the book
Results 1-3 of 84
Page 11
... developed better sensor - based control policies , flexible enough to operate over a broader range of conditions , for a component of the larger power system . In the same way , ADP could be used to improve performance or robustness or ...
... developed better sensor - based control policies , flexible enough to operate over a broader range of conditions , for a component of the larger power system . In the same way , ADP could be used to improve performance or robustness or ...
Page 312
... developed to estimate performance gradients directly from a single sample path ( Sections 12.3.2 , 12.3.3 ) . 2. Develop efficient optimization algorithms with the potential or gradient esti- mates ( a ) Gradient - based optimization ...
... developed to estimate performance gradients directly from a single sample path ( Sections 12.3.2 , 12.3.3 ) . 2. Develop efficient optimization algorithms with the potential or gradient esti- mates ( a ) Gradient - based optimization ...
Page 519
... developed by Shavit and Seems [ 34 ] have been field - tested , indicating that they are more fully developed than others . Seem's PRAC controller uses the temporal pattern of the controlled variable to adjust the proportional and ...
... developed by Shavit and Seems [ 34 ] have been field - tested , indicating that they are more fully developed than others . Seem's PRAC controller uses the temporal pattern of the controlled variable to adjust the proportional and ...
Contents
Foreword | 1 |
Reinforcement Learning and Its Relationship to Supervised Learning | 47 |
ModelBased Adaptive Critic Designs | 65 |
Copyright | |
20 other sections not shown
Other editions - View all
Common terms and phrases
action network actor adaptive critic designs agent algorithm analysis angle applications approach approximate dynamic programming approximate LP backpropagation behavior Bellman equation BPTT chapter computational constraints control law control problems convergence cost critic network curse of dimensionality defined derivatives DHP neurocontroller direct NDP equation error estimate example Figure formulation function approximation fuzzy goal gradient helicopter Heuristic hierarchical IEEE Trans implemented improve initial input iteration learning algorithms learning rate linear programming load Lyapunov function Machine Learning Markov decision processes methods micro-alternator minimize module neural network node nonlinear operating optimal control optimal policy optimization problem output parameters Pareto optimal performance PI controller power system Proc Q-learning reinforcement learning reward robot Section simulation solve space stability stochastic structure supervised learning task techniques Theorem trajectory transition update Utility function value function variables vector voltage weights Werbos