EFFICIENT APPROXIMATE POLICY ITERATION METHODS FOR SEQUENTIAL DECISION MAKING IN REINFORCEMENT LEARNING

منو

" EFFICIENT APPROXIMATE POLICY ITERATION METHODS FOR SEQUENTIAL DECISION MAKING IN REINFORCEMENT LEARNING "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	149820
Doc. No	:	ET21612
Main Entry	:	Michail G. Lagoudakis
Title Proper	:	EFFICIENT APPROXIMATE POLICY ITERATION METHODS FOR SEQUENTIAL DECISION MAKING IN REINFORCEMENT LEARNING
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Reinforcement learning is a promising learning paradigm in which an agent learns howto make good decisions by interacting with an (unknown) environment. This learningframework can be extended along two dimensions: the number of decision makers(single- or multi- agent) and the nature of interaction (collaborative or competitive).This characterization leads to the four decision making situations that are consideredin this thesis and are modeled as Markov decision processes, team Markov decisionprocesses, zero-sum Markov games, and t eam zero-sum Markov games.Existing reinforcement learning algorithms have not been applied widely on real-vSorld problems, mainly because.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	:	TL44787.pdf
Title and statement of responsibility and	:	EFFICIENT APPROXIMATE POLICY ITERATION METHODS FOR SEQUENTIAL DECISION MAKING IN REINFORCEMENT LEARNING [Thesis]