Show simple item record

dc.contributor.advisorFilippakis, Michael
dc.contributor.advisorΦιλιππάκης, Μιχαήλ
dc.contributor.authorTsirovasilis, Ioannis
dc.contributor.authorΤσιροβασίλης, Ιωάννης
dc.publisherΠανεπιστήμιο Πειραιώςel
dc.titleLearning Tetris with reinforcement learningel
dc.typeMaster Thesisel
dc.contributor.departmentΣχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών Συστημάτωνel
dc.description.abstractENThe last decades, scientists have expressed an increasing interest for the game Tetris and more precisely for efficient algorithms that can score the most in-game points. A plethora of approaches have been tried out, including genetic algorithms, linear programming, cross-entropy and natural policy gradient, but none of them competes with experts players playing under no time pressure. In recent years, scientists have started applying reinforcement learning in Tetris as it displays effective results in adapting to video game environments, exploit mechanisms and deliver extreme performances. Current thesis aims to introduce Memory Based Learning, a reinforcement learning algorithm which uses a memory that helps in the training process by replaying past experiences.el
dc.contributor.masterΨηφιακά Συστήματα και Υπηρεσίεςel
dc.subject.keywordArtificial intelligenceel
dc.subject.keywordDeep learningel
dc.subject.keywordReinforcement learningel
dc.subject.keywordNeural networksel

Files in this item


This item appears in the following Collection(s)

Show simple item record

Βιβλιοθήκη Πανεπιστημίου Πειραιώς
Contact Us
Send Feedback
Created by ELiDOC
Η δημιουργία κι ο εμπλουτισμός του Ιδρυματικού Αποθετηρίου "Διώνη", έγιναν στο πλαίσιο του Έργου «Υπηρεσία Ιδρυματικού Αποθετηρίου και Ψηφιακής Βιβλιοθήκης» της πράξης «Ψηφιακές υπηρεσίες ανοιχτής πρόσβασης της βιβλιοθήκης του Πανεπιστημίου Πειραιώς»