Towards the Co-Evolution of Influence Map Tree Based Strategy Game Players

Miles, Christopher E.; Louis, Sushil J.

doi:10.1109/cig.2006.311684

Cited by 34 publications

(23 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Utilising a parallel Steady State GA to co-evolve populations of Influence Map-based Artificial Intelligence (IMAI) agents, each individual in a population represented all the parameters and coefficients for an IM Tree-based representation of game related resource allocations and tactical spatial reasoning. Extending previous research performed by Miles and Louis (2006), in which a GA was used to evolve both the allocation of resource units to game-related objectives and also to co-evolve the Influence Map Trees for tactical spatial reasoning, Miles et al (2007) found the co-evolved game agents were more than capable of beating hand-coded opponents agents within a relatively small number of generations of evolution and eventually evolved to be capable of beating human opponents (Miles et al 2007). …”

Section: Evolutionary Optimisation Of Influence Map-based Game Agent mentioning

confidence: 93%

Machine learning in digital games: a survey

2008

View full text Add to dashboard Cite

Artificial intelligence for digital games constitutes the implementation of a set of algorithms and techniques from both traditional and modern artificial intelligence in order to provide solutions to a range of game dependent problems. However, the majority of current approaches lead to predefined, static and predictable game agent responses, with no ability to adjust during game-play to the behaviour or playing style of the player. Machine learning techniques provide a way to improve the behavioural dynamics of computer controlled game agents by facilitating the automated generation and selection of behaviours, thus enhancing the capabilities of digital game artificial intelligence and providing the opportunity to create more engaging and entertaining game-play experiences. This paper provides a survey of the current state of academic machine learning research for digital game environments, with respect to the use of techniques from neural networks, evolutionary computation and reinforcement learning for game agent control.

show abstract

Section: Evolutionary Optimisation Of Influence Map-based Game Agent mentioning

confidence: 93%

Machine learning in digital games: a survey

2008

View full text Add to dashboard Cite

show abstract

“…Influence maps can be used to determine who is in control of a certain part of a map [5]. Conceptually, influence maps have some similarity with potential fields used in robotics to define motion control.…”

Section: A Decision Makingmentioning

confidence: 99%

“…In [8], an algorithm is proposed that determines where is the best place for Pac-Man to move, based on attractiveness of potential fields, taking into consideration the moving ghosts and dots to eat. In [5], the authors build influence maps into a tree form, where every leaf is a representation of the game state in form of an influence map. From there a genetic algorithm is used to investigate the best strategy.…”

Section: A Decision Makingmentioning

confidence: 99%

Towards the design of a human-like FPS NPC using pheromone maps

Yahyavi

Tremblay

Verbrugge

et al. 2013

2013 IEEE International Games Innovation Conference (IGIC)

View full text Add to dashboard Cite

Abstract-Non-player characters (NPCs) in video games tend to be easily recognized by human players, reducing the sense of immersion and limiting the complexity of character interactions. In this paper we study various aspects of the NPCs performance and how it differs from human players. We provide categorization and metrics for quantifying some aspects of the NPCs performance and provide an in-depth analysis of the behavior of NPCs. We detail how movements, interactions, use of items, and relying on static decision-making schemes result in markedly different behaviors from humans in the popular FPS Quake III. In addition, we propose a framework relying on a special kind of influence map, a pheromone map, which can lead to a more adaptive human-like behavior. These maps can efficiently give a summary of the events in the game world, be adaptive in nature, and be effectively used in the decision making process of NPCs.

show abstract

“…Miles and Louis use influence maps as nodes in trees to determine different game situations and as decision support system [12], [13]. These decisions are queued with priorities into a task queue.…”

Section: A Related Researchmentioning

confidence: 99%

Intelligent moving of groups in real-time strategy games

Danielsiek

Stüer

Thom

et al. 2008

2008 IEEE Symposium on Computational Intelligence and Games

View full text Add to dashboard Cite

Abstract-This paper investigates the intelligent moving and path-finding of groups in real-time strategy (RTS) games exemplified by the open source game Glest. We utilize the technique of Flocking for achieving a smooth and natural movement of a group of units and expect grouping to decrease the amount of unit losses in RTS games. Furthermore, we present a setting in which Flocking will improve the game progress. But we also demonstrate a situation where Flocking fails. To prevent these annoying situations, we combined Flocking with Influence Maps (IM) to find safe paths for the flock in real time. This combination turns out to be an excellent alternative to normal movement in Glest and most likely in other RTS games.

show abstract

Towards the Co-Evolution of Influence Map Tree Based Strategy Game Players

Cited by 34 publications

References 7 publications

Machine learning in digital games: a survey

Machine learning in digital games: a survey

Towards the design of a human-like FPS NPC using pheromone maps

Intelligent moving of groups in real-time strategy games

Contact Info

Product

Resources

About