Co-evolving Real-Time Strategy Game Micro

Adhikari, Navin K; Louis, Sushil J.; Liu, Siming; Spurgeon, Walker

doi:10.1109/ssci.2018.8628750

Cited by 6 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Micromanagement refers to actions involving direct unit control (TeamLiquid 2012; Adhikari et al 2018): unit positioning, specific maneuvers, using special abilities at the right spot and time, etc. Micro was one of the defining characteristics of StarCraft at the time of its release (Dulin 1998;Gamespot Staff 2000).…”

Section: Real-time Control and Interfacementioning

confidence: 99%

StarCraft

Dor

2024

View full text Add to dashboard Cite

The Landmark Video Games book series is the first in the English language in which each book addresses a specific video game or video game series in depth, examining it in the light of a variety of approaches, including game design, genre, form, content, meanings, and its context within video game history. The specific games or game series chosen are historically significant and influential games recognized not only for their quality of gameplay but also for setting new standards, introducing new ideas, incorporating new technology, or otherwise changing the course of a genre or area of video game history. The Landmark Video Games book series hopes to provide an intimate and detailed look at the history of video games through a study of exemplars that have paved the way and set the course that others would follow or emulate, and that became an important part of popular culture. NC

show abstract

Section: Real-time Control and Interfacementioning

confidence: 99%

StarCraft

Dor

2024

View full text Add to dashboard Cite

show abstract

“…The highest fit individual in the population is usually just one player, not a set of n players. Even if the evolutionary algorithm uses elitism, where the best fit individual always survives, being highly fit in one generation may not carry over to future generations with different players (e.g., see [17][18][19]). A player's opponents never change when they are evolved as a set, making the notion of fitness more meaningful.…”

Section: Evolving Player Setsmentioning

confidence: 99%

A Representation for Many Player Generalized Divide the Dollar Games

Greenwood

Ashlock

2023

Games

View full text Add to dashboard Cite

Divide the dollar is a simplified version of a two player bargaining problem game devised by John Nash. The generalized divide the dollar game has n>2 players. Evolutionary algorithms can be used to evolve individual players for this generalized game but representation—i.e., a genome plus a move or search operator(s)—must be carefully chosen since it affects the search process. This paper proposes an entirely new representation called a demand matrix. Each individual in the evolving population now represents a collection of n players rather than just an individual player. Players use previous outcomes to decide their choices (bids) in the current round. The representation scales linearly with the number of players and the move operator is a variant of an evolution strategy. The results indicate that this proposed representation for the generalized divide the dollar game permits the efficient evolution of large player populations with high payoffs and fair demand sets.

show abstract

“…RTS games were also investigated in [17]. Again, influence maps were used, but this time they were combined with potential fields.…”

Section: Related Workmentioning

confidence: 99%

Classical Formation Patterns and Flanking Strategies as a Result of Utility Maximization

Scukins

Ögren

2019

IEEE Control Syst. Lett.

View full text Add to dashboard Cite

In this paper, we show how classical tactical formation patterns and flanking strategies, such as the line formation and the enveloping maneuver, can be seen as the result of maximizing a natural formation utility.The problem of automatic formation keeping is extremely well studied within the areas of control and robotics, but the reasons for choosing a particular formation shape and position is much less so.By analyzing a situation with two adversarial teams of agents facing each other, we show that natural assumptions regarding the target selection of the agents and decreasing weapon efficiency over distance, can be used to optimize a measure of utility over agent positions. This optimization in turn results in formations and positions that are very similar to the ones being used in practice. We present both analytical results for simple examples as well as numerical results for more complex situations.

show abstract

Co-evolving Real-Time Strategy Game Micro

Cited by 6 publications

References 28 publications

StarCraft

StarCraft

A Representation for Many Player Generalized Divide the Dollar Games

Classical Formation Patterns and Flanking Strategies as a Result of Utility Maximization

Contact Info

Product

Resources

About