Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Design and development of autonomous agent for the Mastermind board game

Manesiotis Athanasios

Full record


URI: http://purl.tuc.gr/dl/dias/6FCBA189-D878-4D4C-BC2F-6F64DD4BC6EA
Year 2023
Type of Item Diploma Work
License
Details
Bibliographic Citation Αθανάσιος Μανεσιώτης, "Σχεδίαση και ανάπτυξη αυτόνομου πράκτορα για το επιτραπέζιο παιχνίδι Mastermind", Διπλωματική Εργασία, Σχολή Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών, Πολυτεχνείο Κρήτης, Χανιά, Ελλάς, 2023 https://doi.org/10.26233/heallink.tuc.95291
Appears in Collections

Summary

Artificial Intelligence (AI) deals with the design and construction of intelligent entities/machines, capable of executing functions attributable to human intelligence. These entities/machines that can act efficiently and safely in a wide range of new situations are called intelligent agents. A rational agent is an intelligent agent, that can act in such way as to maximize the expected utility under conditions of uncertainly, i.e. to choose actions that are expected to maximize its performance metric. Board games have been an important area of research for the development and testing of AI applications, with significant successes and victories over humans in competitive two-player games. This diploma thesis focuses on the design and development of autonomous agents for the board game Mastermind. The agents can cope with both the classic version of the game and the more complex levels of difficulty developed within this thesis. In addition to the analysis and the comparison of the implemented agents, the thesis provides a user-friendly graphical interface for the user to visualize and immediately understand the results of the strategies of the agents. In addition, the user is given the opportunity to play the game on his own. Both the code for the graphical interface and the strategies followed by the agents were implemented in Java, taking advantage of the possibilities provided by this programming language. The extracted results are quite satisfactory, since in the classic version of the game, the proposed agent with some of the implemented strategies detects the hidden color code in a maximum of five (5) attempts.

Available Files

Services

Statistics