This paper presents a multi-agent system that handles unit micromanagement using online machine learning in real time strategy games. We used rtNEAT algorithm in order to obtain customized neural network topologies, thus avoiding to complex network architecture. We use an ontology based template to create suitable input and outputs for unit agents enabling them to cooperate and form teams for t...

In real-time strategy games like StarCraft, skilled players often block the entrance to their base with buildings to prevent the opponent’s units from getting inside. This technique, called “walling-in”, is a vital part of player’s skill set, allowing him to survive early aggression. However, current artificial players (bots) do not possess this skill, due to numerous inconveniences surfacing d...

Artificial Intelligence (AI) has been widely used in modern video games for creating interactive non-player characters (NPC) and opponents. Although the design of NPC enemy AI has been studied for years and has many commercial implementations such as StarCraft, World of Warcraft, a good AI for NPC companions is still under-analyzed. In this thesis we investigate several approaches for solving c...

For many networked games, such as the Defense of the Ancients and StarCraft series, the unofficial leagues created by players themselves greatly enhance user-experience, and extend the success of each game. Understanding the social structure that players of these games implicitly form helps to create innovative gaming services to the benefit of both players and game operators. But how to extrac...

ference is the definitive point of interaction between entertainment software developers interested in AI and academic and industrial AI researchers. The conference is targeted at the research and commercial communities, promoting AI research and practice in the context of interactive digital entertainment systems with an emphasis on commercial video games. AIIDE 2010 was held October 11–13, 20...

For moving target search algorithms, we are considering the case of heuristic search where the goal may change during the course of the search. One motivating application lies with navigation of an autonomous police vehicle chasing a villain [5] in a possibly initially unknown environment under real-time constraints. In this scenario, we would like to assure that the autonomous vehicle can quic...

Value function factorization via centralized training and decentralized execution is promising for solving cooperative multi-agent reinforcement tasks. One of the approaches in this area, QMIX, has become state-of-the-art achieved best performance on StarCraft II micromanagement benchmark. However, monotonic-mixing per agent estimates QMIX known to restrict joint action Q-values it can represen...

When I was seven years old, my parents bought me and my brother a Nintendo Entertainment System, which they would eventually refer to as “The Idiot Box.” There was an implicit assumption (one that persists in much of the general public today) that video games were simply a toy and nothing of real substance could be gained from them. Considering this, and the prevalence of video games in society...

A brood pheromone is a chemical or mixture of chemicals released by immature stages that elicits a behavioral response in conspecific adults. The current literature devoted to brood pheromones in several ant species does not prove the existence of such a pheromone or even of brood-specific chemicals. The possibility of a food response or a nestmate recognition response, two of the most confound...

Hot climate is a major limiting factor of broiler production in tropical and subtropical regions. The use of standard stocks in hot climates may result in large economic losses because genotypes selected in temperate climates may respond differently to the high ambient temperatures in hot regions or seasons. The summer and fall in Izmir, Turkey, provided the natural hot and temperate climates, ...