There are many games that have been a challenge to Research in Artificial Intelligence. One such game is Settlers of Catan (SoC). The purpose of this thesis is to develop a Multi-agent player for SoC. Although it is difficult to focus on all the dimensions of the game during implementation, therefore a good enough solution is proposed. An emphasis is placed on building a good trader for the player. Once a working solution had been built, the player was tested against other players which included human players as well as bots.
Contents
1 INTRODUCTION
1.1 BACKGROUND
1.2 AIMS AND OBJECTIVES
1.3 RESEARCH QUESTIONS
1.4 PROBLEMS AND CHALLENGES
1.5 RESEARCH METHODOLOGY
1.6 CONTRIBUTION
2 SETTLERS OF CATAN (SOC)
2.1 OVERVIEW OF THE GAME
2.2 HOW TO PLAY THE GAME
2.3 STRATEGIES IN THE GAME
2.3.1 The Ore-Grain Strategy
2.3.2 The Wood-Brick Strategy
2.3.3 The Card Builder Strategy
2.3.4 The Balance Strategy
2.3.5 The Rare Resource Strategy
2.3.6 The Monopoly and Cartel Strategy
2.4 SOME ADDITIONAL CONSIDERATIONS
3 IMPLEMENTATION
3.1 MULTI-AGENT SYSTEM
3.2 DESIGN OF THE SYSTEM
3.3 IMPLEMENTATION DETAILS
3.3.1 jSettlers Server
3.3.2 jSettlers Client
3.4 PROJECT OVERVIEW
3.4.1 Tools and Technologies
3.4.2 Project Directory Structure
3.4.3 Player Implementation
4 EXPERIMENTAL SETUP
4.1 IMPORTANT CONSIDERATIONS
4.2 ENVIRONMENT
4.3 PROBLEMS
4.4 EXECUTION
5 ANALYSIS AND RESULTS
5.1 IMPACT OF DIFFERENT FACTORS ON THE PERFORMANCE OF THE PLAYER
5.1.1 Tuning Different Parameters
5.1.2 Collection of valuable resources compared to resources needed by the player
5.1.3 Collection of resources needed in trade compared to other players’ position in trade
5.1.4 Doing dumb trades compared to sensible trades
5.1.5 Overall strategies and Comparisons
5.2 RESULTS
6 DISCUSSIONS
7 CONCLUSION
8 FUTURE WORK
Author: Rashdan Raees Natiq. Haseeb Saleem
Source: Blekinge Institute of Technology
Download URL 2: Visit Now