Wireless Application Development has become a major area of research in recent times. With the increasing availability of wireless technologies such as cellular, Bluetooth, Infrared etc. it has become essential to develop applications that suit the various types of hardware that support such wireless technologies. The goal of this thesis is to explore the motivations behind application development methodologies and the tools associated with it, for small mobile devices that employ cellular technologies. Due to extremely high demand of cell phones among people who have over the years become extra mobile, there has been a trend of decreasing costs for users for the last several years. As more people start using these devices every day the demand for support of various applications and services are on the rise. This thesis will explore the leading application development tools and technologies for small mobile devices WAP (Wireless Application Protocol), J2ME (Java 2 Platform, Micro Edition) and some others. This thesis will also take a brief look into cellular network technology termed 3G, in terms of its usefulness for applications developed using the aforementioned technologies. The thesis includes the development of a J2ME application using a wireless device emulator.

Αντικείμενο της Διπλωματικής εργασίας είναι η μεταφορά ενός παιχνιδιού στρατηγικής, πού έχει αναπτυχθεί με γνώμονα τους κανόνες της Ενισχυτικής Μάθησης (Reinforcement Learning) & των Νευρωνικών δικτύων (Neural Networks), σε πλατφόρμα κινητού τηλεφώνου 6ης γενιάς & μέσω διαδικτύου με σκοπό την εκπαίδευσης του συστήματος από τον απλό χρήστη. Σκοπός της διπλωματικής εργασίας είναι η σχεδίαση, ανάπτυξη του συστήματος λογισμικού βασισμένου σε τεχνολογίες διαδικτύου & κινητής τηλεφωνίας. Η Παρούσα εργασία επικεντρώνεται σε τρεις τομείς: • Έρευνα υφιστάμενων mobile τεχνολογιών • Δυνατότητα επανασχεδιασμού εφαρμογής με χρήση τεχνολογιών mobile internet • Έλεγχος υφιστάμενης δυνατότητας επανασχεδίασης και επαναϋλοποίησης του παιχνιδιού με χρήση άλλων συστημάτων (πλατφόρμων) σε συνδυασμό με χρήση ενισχυτικής μάθησης. / In this paper we review our work on th acquisition of game-playing capabilitiew by a computer , when the only source of knowledge comes from extended self-play and sparsely dispersed human-expert play. We summarily present experiment that showhow a reinforcement learning backbone coupled with neural networks for approximation can indeed serve as amechanism of the acquisition oof game playing skill and we derive game interestingness measures that are inexpensive and strightforward to compute, yert also capture the relative quality of the game playing engine.