In this paper we propose using a Genetic Algorithm to optimize the placement of buildings in Real-Time Strategy games. Candidate solutions are evaluated by running base assault simulations. We present experimental results in SparCraft — a StarCraft combat simulator — using battle setups extracted from human and bot StarCraft games. We show that our system is able to turn base assaults that are ...

Real-Time Strategy (RTS) video games have proven to be a very challenging application area for artificial intelligence research. Existing AI solutions are limited by vast state and action spaces and real-time constraints. Most implementations efficiently tackle various tactical or strategic sub-problems, but there is no single algorithm fast enough to be successfully applied to big problem sets...

Real-time strategy games, such as Wargus, are examples of complex learning and planning domains that present unique challenges to AI and machine learning. These games usually comprise a large number of states, actions, resources, and decisions that a player needs to take into consideration, while, at the same time, the current game situation is influenced and modified by opponents. With the dri...

Historically, real-time strategy video games, such as Starcraft (Blizzard Entertainment, 1999) and Command and Conquer (Westwood Studios, 1995), were intended to be played on desktop or laptop computers, with interfaces that afford the user dozens of keys and key combinations, mouse gestures including clicking and dragging, and several mouse buttons to further complicate the interface while all...

Video games are complex simulation environments with many real-world properties that need to be addressed in order to build robust intelligence. In particular, realtime strategy games provide a multi-scale challenge which requires both deliberative and reactive reasoning processes. Experts approach this task by studying a corpus of games, building models for anticipating opponent actions, and p...

We consider the problem of tactical assault planning in real-time strategy games where a team of friendly agents must launch an assault on an enemy. This problem offers many challenges including a highly dynamic and uncertain environment, multiple agents, durative actions, numeric attributes, and different optimization objectives. While the dynamics of this problem are quite complex, it is ofte...

Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tree Search (MCTS) algorithms called näıve sampling, based on a variant of the Multiarmed Bandit problem called Combinatorial Multi-armed Bandits (CMAB). We analyze the theoretical properties of several variants of näıve...

The implementation of AI in commercial games is usually based on low level designs that makes the control predictable, unadaptive, and non reusable. Recent algorithms such as HTN or GOAP prove that higher levels of abstraction can be applied for better performance. We propose that approaches based on Organizational Theory can help providing a sound alternative for these implementations. In this...

We present CLASSQL, a multi-agent model for playing real-time strategy games, where learning and control of our own team’s units is decentralized; each agent uses its own reinforcement learning process to learn and control units of the same class. Coordination between these agents occurs as a result of a common reward function shared by all agents and synergistic relations in a carefully crafte...

In this paper we propose using a Genetic Algorithm to optimize the placement of buildings in Real-Time Strategy games. Candidate solutions are evaluated by running base assault simulations. We present experimental results in SparCraft — a StarCraft combat simulator — using battle setups extracted from human and bot StarCraft games. We show that our system is able to turn base assaults that are ...