Implementacija MCTS algoritma u obrazovnoj aplikaciji za igranje društvene igre "4 u nizu"

master's thesis

• Title (english): Implementation of the Monte Carlo Tree Search Algorithm in an Educational Application for Playing the Board Game "Connect Four."
• Author: Denis Pipalović
• Mentor: Tomislav Jagušt (mentor)
• Committee member: Tomislav Jagušt (predsjednik povjerenstva)
• Committee member: Gordan Gledec (član povjerenstva)
• Committee member: Marko Horvat (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-05, Croatia

Abstract

U sklopu ovog rada razvijena je aplikacija za igranje i učenje igranja društvene igre „4 u nizu” (engl. „Connect 4”). Aplikacija koristi Monte Carlo Tree Search (MCTS) algoritam za određivanje kvalitetnih poteza računalnog protivnika, kao i za preporučivanje poteza igraču. Unutar ovog rada opisano je sve što je potrebno za razumijevanje MCTS algoritma i njegove implementacije u aplikaciji koja pruža moderan pristup učenju.

Abstract (english)

In this thesis, an application for playing and learning to play the board game "Connect Four" has been developed. The application uses the Monte Carlo Tree Search (MCTS) algorithm to determine the quality of the moves of the computer opponent, as well as to recommend moves to the player. This thesis describes everything needed to understand the MCTS algorithm and its implementation in an application that provides a modern approach to learning.

• Keywords: MCTS; igra; aplikacija; društvene igre; „4 u nizu”; učenje; strategija; igrifikacija; obrazovanje
• Keywords (english): MCTS; game; application; board games; "Connect Four"; learning; strategy; gamification; education
• Language: croatian
• URN:NBN: urn:nbn:hr:168:750559
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 21:53:12