خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 150985
Doc. No : ET22777
Main Entry : MANISH MEHTA
Title Proper : ROBOTIC SOCCER SIMULATOR USING REINFORCEMENT LEARNING WITH CLUSTERING
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : In today's world, there are many applications that cannot be monitored manually atall times. The number of such applications is increasing daily. Thus there is an urgentneed to develop intelligent applications that learn based on their experience.We delve into a Machine Learning method called Reinforcement Learning. Thislearning method works well even if the agent has no knowledge about its surroundings.An application or an agent learns by trial-and-error. It can get feedback in the form ofrewards or punishments after every action. In some cases, the agent might not getfeedback after every action. It might just get a feedback on reaching the ultimate goal.These rewards are propagated to actions that were taken earlier. This is also calleddelayed reward assignment. The aim of a reinforcement learning agent is to come up witha look-up table, which can be used to take.,....-...,..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 : TL46003.pdf
Title and statement of responsibility and : ROBOTIC SOCCER SIMULATOR USING REINFORCEMENT LEARNING WITH CLUSTERING [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)