A review of computational intelligence in RTS games

Lara-Cabrera, Raúl; Cotta, Carlos; Fernández-Leiva, Antonio J.

doi:10.1109/foci.2013.6602463

Cited by 33 publications

(20 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Probably these aspects make these type of games less researched than their turn-based games counterparts [12], despite the great number of know open challenges such as: adversarial real-time planning, decision making under uncertainty of partially observable domains, learning from experience or observation, opponent modeling, spatial and temporal reasoning, navigation, resource management and collaboration [13], [14].…”

Section: B Artificial Intelligence In Rts Gamesmentioning

confidence: 99%

Evolving Swarm Intelligence for Task Allocation in a Real Time Strategy Game

Tavares

Azpúrua

Chaimowicz

2014

2014 Brazilian Symposium on Computer Games and Digital Entertainment

View full text Add to dashboard Cite

Real time strategy games are complex scenarios where multiple agents must be coordinated in a dynamic, partially observable environment. In this work, we model the coordination of these agents as a task allocation problem, in which specific tasks are given to the agents that are more suited to execute them. We employ a task allocation algorithm based on swarm intelligence and adjust its parameters using a genetic algorithm. To evaluate this approach, we implement this coordination mechanism in the AI of a popular video game: StarCraft: BroodWar. Experiment results show that the genetic algorithm enhances performance of the task allocation algorithm. Besides, performance of the proposed approach in matches against StarCraft's native AI is comparable to that of a tournament-level software-controlled player for StarCraft.

show abstract

Section: B Artificial Intelligence In Rts Gamesmentioning

confidence: 99%

Evolving Swarm Intelligence for Task Allocation in a Real Time Strategy Game

Tavares

Azpúrua

Chaimowicz

2014

2014 Brazilian Symposium on Computer Games and Digital Entertainment

View full text Add to dashboard Cite

show abstract

“…In [8], we provide a web link where the reader can play a number of maps (with 5 planets), of diverse difficulty, that were generated by our proposed PCG method (and by considering all the fitness functions defined here). We have performed a preliminary study on the system's capabilities to generate maps of diverse difficulty: the web platform has collected the participation of 58 unique users and an average number of votes per map of 55, because not all participants played and evaluated each of the 21 maps (see Table 1).…”

Section: Discussionmentioning

confidence: 99%

“…is a game implemented by the authors of this paper [8], that has been inspired by the n-body problem, which includes some additional features that transforms an interactive simulation into a playable environment. In the following paragraphs we discuss some articular features of our game:…”

Section: The Game: Gravityvolve!mentioning

confidence: 99%

“…In this context, this paper presents the following contributions: first, it introduces Gravityvolve!, a physics-based simulation video game that we have implemented, inspired by the n-body problem, a classical problem in the field of physics and mathematics, which can be used by the CI/AI community for research purposes [8]. Moreover, this paper proposes a method, that can be generalized to other (not-necessarily physics-based) games, to procedurally design maps of diverse solving complexity (i.e., of distinct levels of difficult); the proposal consists of an evolutionary algorithm (EA) which is spatially-structured in a number of sub-populations that are co-evolved separately according to different properties required by the individuals of each sub-population (which should supposedly guarantee diversity).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Spatially-Structured PCG Method for Content Diversity in a Physics-Based Simulation Game

Lara-Cabrera

Alcoba

Fernández-Leiva

2016

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract. This paper presents a spatially-structured evolutionary algorithm (EA) to procedurally generate game maps of different levels of difficulty to be solved, in Gravityvolve!, a physics-based simulation videogame that we have implemented and which is inspired by the nbody problem, a classical problem in the field of physics and mathematics. The proposal consists of a steady-state EA whose population is partitioned into three groups according to the difficulty of the generated content (hard, medium or easy) which can be easily adapted to handle the automatic creation of content of diverse nature in other games. In addition, we present three fitness functions, based on multiple criteria (i.e:, intersections, gravitational acceleration and simulations), that were used experimentally to conduct the search process for creating a database of maps with different difficulty in Gravityvolve!.

show abstract

“…RTS games have been used many times as a tool to measure the efficiency and performance of artificial intelligence techniques [7]. This kind of games offer several fundamental AI research problems, such as adversarial real-time planning, opponent modelling, spatial and temporal reasoning, decision making under uncertainty and resource management.…”

Section: Introductionmentioning

confidence: 99%

A self-adaptive evolutionary approach to the evolution of aesthetic maps for a RTS game

Lara-Cabrera

Cotta

Fernández-Leiva

2014

2014 IEEE Congress on Evolutionary Computation (CEC)

Self Cite

View full text Add to dashboard Cite

Procedural content generation (PCG) is a research field on the rise, with numerous papers devoted to this topic. This paper presents a PCG method based on a self-adaptive evolution strategy for the automatic generation of maps for the real-time strategy (RTS) game Planet Wars. These maps are generated in order to fulfill the aesthetic preferences of the user, as implied by her assessment of a collection of maps used as training set. A topological approach is used for the characterization of the maps and their subsequent evaluation: the sphere-of-influence graph (SIG) of each map is built, several graph-theoretic measures are computed on it, and a feature selection method is utilized to determine adequate subsets of measures to capture the class of the map. A multiobjective evolutionary algorithm is subsequently employed to evolve maps, using these feature sets in order to measure distance to good (aesthetic) and bad (non-aesthetic) maps in the training set. The so-obtained results are visually analyzed and compared to the target maps using a Kohonen network.

show abstract

A review of computational intelligence in RTS games

Cited by 33 publications

References 46 publications

Evolving Swarm Intelligence for Task Allocation in a Real Time Strategy Game

Evolving Swarm Intelligence for Task Allocation in a Real Time Strategy Game

A Spatially-Structured PCG Method for Content Diversity in a Physics-Based Simulation Game

A self-adaptive evolutionary approach to the evolution of aesthetic maps for a RTS game

Contact Info

Product

Resources

About