HIERARCHICAL REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION FOR ADAPTIVE CONTROL

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" HIERARCHICAL REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION FOR ADAPTIVE CONTROL "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149863
Doc. No	:	ET21655
Main Entry	:	MARGARET MARY SKELLY
Title Proper	:	HIERARCHICAL REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION FOR ADAPTIVE CONTROL
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Reinforcement learning is an artificial intelligence technique whereby an agentdiscovers which actions lead to optimal task performance through interaction with itsenvironment. Although reinforcement learning is usually employed to find optimalproblem solutions in unchanging environments, a reinforcement learning agent can bemodified to continually explore and adapt in a dynamic environment, carrying out a formof direct adaptive control. In the adaptive control setting, the reinforcement learningagent must be able to learn and adapt quickly enough to compensate for the dynamics ofthe environment. Since reinforcement learning is known to converge slowly to optimalityin stationary environments, the use of abstraction and changes in task representation areexamined as a means to accelerate reinforcement learning. Various levels of abstraction..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL44833.pdf
Title and statement of responsibility and	:	HIERARCHICAL REINFORCEMENT LEARNING WITH FUNCTION APPROXIMATION FOR ADAPTIVE CONTROL [Thesis]