Transcription of An Introduction to Markov Decision Processes
{{id}} {{{paragraph}}}
Example: dental hygienist
An Introduction to Markov Decision Processes
MDP Tutorial - 1An Introduction toMarkov Decision ProcessesBob GivanRon ParrPurdue UniversityDuke UniversityMDP Tutorial - 2 OutlineMarkov Decision Processes defined (Bob) Objective functions PoliciesFinding Optimal solutions (Ron) Dynamic programming Linear programmingRefinements to the basic model (Bob) Partial observability factored representationsMDP Tutorial - 3 Stochastic Automata with UtilitiesAMarkov Decision Process (MDP) modelcontains: A set of possible world statesS A set of possible actionsA A real valued reward functionR(s,a) A descriptionTof each action s effects in each :the effects of an actiontaken in a state depend only on that state and not on theprior Tutorial - 4 Stochastic Automata with UtilitiesAMarkov Decision Process (MDP) modelcontains: A set of possible world statesS A set of possible actionsA A real valued reward functionR(s,a) A descriptionTof each action s effects in each :the effects of an actiontaken in a state depend only on that state and not on theprior Tutorial - 5 Representing ActionsDeterministic Actions: T : For each state and action we specify a new Actions: T:For each state and action wespecify a probability distribution over next the distributionP(s |s,a).
• MDP solution focuses critically on expected value • Contrast safety properties which focus on worst case ... • Typically exploiting factored state representation • Typically exploiting (near) conditional independence properties of the belief state factors. Title: mdp-tutorial
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: