Handbook of Learning and Approximate Dynamic ProgrammingJennie Si
|
From inside the book
Results 1-3 of 72
Page 212
... behaviors . The larger an agent's repertoire of behaviors becomes , the more critical this kind of background knowledge . Committing to behaviors Finally , choices are limited by requiring long - term com- mitment to a behavior . It is ...
... behaviors . The larger an agent's repertoire of behaviors becomes , the more critical this kind of background knowledge . Committing to behaviors Finally , choices are limited by requiring long - term com- mitment to a behavior . It is ...
Page 216
... behavior results in a sequence of primitive actions being performed . The value of the behavior is equal to the value of that sequence . Thus if behavior B is initiated in state s , and terminates sometime later in state st + k then the ...
... behavior results in a sequence of primitive actions being performed . The value of the behavior is equal to the value of that sequence . Thus if behavior B is initiated in state s , and terminates sometime later in state st + k then the ...
Page 223
... behavior . However once such a recursively optimal policy has been learned , it can be improved by switching to selecting primitive actions based on their global Q - value instead . There is ... BEHAVIOR LEARNING 223 Intra-Behavior Learning.
... behavior . However once such a recursively optimal policy has been learned , it can be improved by switching to selecting primitive actions based on their global Q - value instead . There is ... BEHAVIOR LEARNING 223 Intra-Behavior Learning.
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