|
|
Strategic Game Based on Multiagent Systems
Knapek, Petr ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on designing and implementing system, that adds learning and planning capabilities to agents designed for playing real-time strategy games like StarCraft. It will explain problems of controlling game entities and bots by computer and introduce some often used solutions. Based on analysis, a new system has been designed and implemented. It uses multi-agent systems to control the game, utilizes machine learning methods and is capable of overcoming oponents and adapting to new challenges.
|
|
|
Intelligent System for the SSCAI Tournament
Horázný, Václav ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
In this work I focus on the creation of artificial intelligence to meet the conditions for the competition SSCAI Tournament. It contains the characteristics and gameplay mechanics of the game Starcraft: Brood War, a description of the rules of that competition, usually played kinds of strategies focusing on the Zerg civilization, namely strategy Pool Rush. In the competition I was on a shared 10th and 11th place out of 42 participants. I have created the artificial intelligence for the game Starcraft: Brood War (1.16.1). The work includes the implementation of two agents ScoutManager and DefenseManager. These agents are already connected to created agents of the project BWSAL. I used the development environment Microsoft Visual Studio 2008 (9.0). To launch artificial intelligence it is required to use the program Chaoslauncher and to use libraries BWAPI and BWTA. Work includes comparing my created program with other stakeholders, both in terms of the method of implementation, as well as by specifically chosen strategies.
|
|
|
Mythic structures and religious motives in the universe of StarCraft computer game series.
Michalič, Robert ; Kostičová, Zuzana (advisor) ; Petříček, Miroslav (referee)
The goal of this work is to provide the reader with an interpretation of races, factions and storyline of the Starcraft game series universe from the perspective of religious studies and to set its results into context of modern spiritual beliefs collectively called New Age. First part of the work analyzes narrative elements which are found in races and factions of Starcraft univerze and reaches the conclusion that through them the game operates with religiously relevant classification categories of purity and dirtiness, order and chaos. The second part utilizes these results in an analysis of narrative structures understood as relations and interactions between particular races and factions, and shows that categories of order and chaos/purity and dirtiness are functionally analogous to Victor Turner's categories of structure and anti-structure. Conclusion of this analysis claims that Starcraft thematizes the problem of one's oppozite's prevalence over the other. The third part summarizes conclusions of both previous parts, gives examples of order/chaos relations in historical religions and shows how narrative structures present these beliefs as problematic. Subsequently this work points out the identical beliefs celebrating the balance between opposites found in New Age, tries to explain the...
|
|
|
Strategic Game Based on Multiagent Systems
Knapek, Petr ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on designing and implementing system, that adds learning and planning capabilities to agents designed for playing real-time strategy games like StarCraft. It will explain problems of controlling game entities and bots by computer and introduce some often used solutions. Based on analysis, a new system has been designed and implemented. It uses multi-agent systems to control the game, utilizes machine learning methods and is capable of overcoming oponents and adapting to new challenges.
|
|
|
Possible application of e-Sports on Czech television
Juna, Petr ; Štoll, Martin (advisor) ; Chladová, Marta (referee)
The bachelor thesis deals with the question of the possible involvement of electronic sport or e-Sport in the broadcast of Czech Television. E-Sport is a rapidly growing sector that attracts especially the younger part of the population. This phenomenon is tracked by millions of people around the world, and its popularity is expected to rise further. In the United States, e- Sport is already included among the sporting industries that can help players to get a college scholarship or easier entry into the country. In South Korea, where e-Sport is one of the largest social themes, players are celebrities and this year's presidential election has shown how important part of culture is progaming for this country. Even in the Czech Republic, e- Sport is already being broadcast, quite successfully on the Prima COOL channel. I also considered the possibility of engaging based on research that Czech Television itself is making every year. Concerning the average weekly intervention and whether the audience is offered programs "appropriate to their tastes and interests", it became clear that Czech Television had relatively low weekly coverage and content satisfaction among spectators from 18 to 24 (or 35 years of age respectively ). If the public broadcasting media were to decide, it could increase their audience...
|
|
|
Integrating Probabilistic Model for Detecting Opponent Strategies Into a Starcraft Bot
Šmejkal, Pavel ; Černý, Martin (advisor) ; Bída, Michal (referee)
Recent research in artificial intelligence (AI) for real time strategies (RTS) has shown a great need for a computer controlled agent (bot) to be able to adapt its strategy in response to opponent's actions. While some progress has been made in detecting opponent's strategies offline, there has not been much success in using this information to guide in-game decisions. We present a version of UAlbertaBot enhanced by existing probabilistic algorithm for supervised learning from replays and strategy prediction. Bot that adapts its strategies has proved to be superior to a random bot as we show in simulated StarCraft: Brood War AI tournament. Our work exposes the importance of scouting and strategy adaptation. By further improvement of strategies, a bot capable of competing with human players may be created.
|
|
|
Multi-agent pathfinding with air transports
Kozma, Matouš ; Černý, Martin (advisor) ; Děchtěrenko, Filip (referee)
In most real-time strategy (RTS) games the problem of finding the shortest path for multiple units in real-time has to be solved many times during one match. That problem is known to be difficult, but some games require solving an even more complicated version of the problem where, in addition to land-based units, there are aerial transports, which are able to move everywhere around the map and to load a unit at one place and unload it somewhere else. In this thesis we introduce a new family of algorithms based on a greedy algorithm, which also serves as a basis for the primitive solutions used in games today. We implement these algorithms in the RTS game Starcraft and evaluate their effectiveness. From these tests we choose the one with the best performance as the solution of this thesis.
|
|
|
Mythic structures and religious motives in the universe of StarCraft computer game series.
Michalič, Robert ; Kostičová, Zuzana (advisor) ; Petříček, Miroslav (referee)
The goal of this work is to provide the reader with an interpretation of races, factions and storyline of the Starcraft game series universe from the perspective of religious studies and to set its results into context of modern spiritual beliefs collectively called New Age. First part of the work analyzes narrative elements which are found in races and factions of Starcraft univerze and reaches the conclusion that through them the game operates with religiously relevant classification categories of purity and dirtiness, order and chaos. The second part utilizes these results in an analysis of narrative structures understood as relations and interactions between particular races and factions, and shows that categories of order and chaos/purity and dirtiness are functionally analogous to Victor Turner's categories of structure and anti-structure. Conclusion of this analysis claims that Starcraft thematizes the problem of one's oppozite's prevalence over the other. The third part summarizes conclusions of both previous parts, gives examples of order/chaos relations in historical religions and shows how narrative structures present these beliefs as problematic. Subsequently this work points out the identical beliefs celebrating the balance between opposites found in New Age, tries to explain the...
|
|
|
Automatic System for Starcraft Game Playing
Skácel, Dalibor ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
This thesis focuses on artificial intelligence principles used in komputer games and their demonstration by implemented automatic system for playing Starcraft. This system uses methods such as: decision trees, finite state machines and it handles decision making in real time environment, control of multiple units with different abilities and works with partial informatik about opponent. Starcraft: Broodwar is one of the most famous real time strategy games and it was chosen for this thesis for its balance and available application interface for controlling the game. The goal is to show artificial intelligence methods in praxis and to create a system which is competitive against other systems in SSCAI (Student Starcraft AI Tournament) competition and even against human players.
|
|
|
Intelligent System for the SSCAI Tournament
Horázný, Václav ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
In this work I focus on the creation of artificial intelligence to meet the conditions for the competition SSCAI Tournament. It contains the characteristics and gameplay mechanics of the game Starcraft: Brood War, a description of the rules of that competition, usually played kinds of strategies focusing on the Zerg civilization, namely strategy Pool Rush. In the competition I was on a shared 10th and 11th place out of 42 participants. I have created the artificial intelligence for the game Starcraft: Brood War (1.16.1). The work includes the implementation of two agents ScoutManager and DefenseManager. These agents are already connected to created agents of the project BWSAL. I used the development environment Microsoft Visual Studio 2008 (9.0). To launch artificial intelligence it is required to use the program Chaoslauncher and to use libraries BWAPI and BWTA. Work includes comparing my created program with other stakeholders, both in terms of the method of implementation, as well as by specifically chosen strategies.
|
guest ::
