Game AI revisited

@inproceedings{Yannakakis2012GameAR,
  title={Game AI revisited},
  author={Georgios N. Yannakakis},
  booktitle={CF '12},
  year={2012}
}
More than a decade after the early research efforts on the use of artificial intelligence (AI) in computer games and the establishment of a new AI domain the term ``game AI'' needs to be redefined. Traditionally, the tasks associated with game AI revolved around non player character (NPC) behavior at different levels of control, varying from navigation and pathfinding to decision making. Commercial-standard games developed over the last 15 years and current game productions, however, suggest… 

Figures from this paper

From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI

TLDR
The algorithms and methods that have paved the way for these breakthroughs are reviewed, including that advances in Game AI are starting to be extended to areas outside of games, such as robotics or the synthesis of chemicals.

A Panorama of Artificial and Computational Intelligence in Games

This paper attempts to give a high-level overview of the field of artificial and computational intelligence (AI/CI) in games, with particular reference to how the different core research areas within

When Are We Done with Games?

TLDR
It is concluded that Dota 2 and StarCraft II are not yet mastered by AI as they so far only have been able to win against top professionals in limited competition structures in restricted variants of the games.

AI for game production

TLDR
A confluence of four major forces at play in the games industry today, together producing a wealth of data that opens unique research opportunities and challenges for Game AI in game production is characterized.

Horizontal Scaling With a Framework for Providing AI Solutions Within a Game Company

TLDR
This paper looks beyond the video games themselves to the application of AI techniques within the ecosystems that produce them, and EA has been delivering a wide range of AI solutions throughout the company during the last two years.

General general game AI

TLDR
This paper builds on the general game-playing paradigm and expands it to cater for all core AI tasks within a game design process, including general player experience and behavior modeling, general non-player character behavior, general AI-assisted tools, general level generation and complete game generation.

The Case for Usable AI: What Industry Professionals Make of Academic AI in Video Games

TLDR
While academic (games) AI research tends to focus on problem-solving capacity, industry professionals highlight the importance of "usability aspects of AI'': the ability to produce plausible outputs, computational performance and ease of implementation.

Design methodology of analytical games for knowledge acquisition

TLDR
This work introduces a framework to provide a structured guidance on the aspects to be factored in the different design phases of an analytical game, including the potential impact of the adoption of automation and autonomy.

Teaming up with Artificial Intelligence: The Human in the Loop of Serious Game Pathfinding Algorithms

TLDR
In the present study, pathfinding algorithms with and without human interventions to the algorithms are investigated, finding some evidence that in this particular pathfinding problem human interventions result in superior results as the MAXMIN Ant System algorithm.

Special Issue on Computational Aesthetics in Games

A GENT-BASED artificial intelligence (AI) research, traditionally, seeks to optimize the performance of artificial agents in their given domains. In the area of games, however, this does not mean
...

References

SHOWING 1-10 OF 74 REFERENCES

Human-Level AI's Killer Application: Interactive Computer Games

TLDR
It is suggested that interactive computer games provide a rich environment for incremental research on human-level AI and the research issues and AI techniques that are relevant to each of these roles.

Player Modeling for Adaptive Games

TLDR
Using player modeling, a game's A1 can adapt both during the course of a single play as well as over multiple sessions, resulting in a computer opponent that changes and evolves with time to suit the player.

Research in human-level AI using computer games

TLDR
Simulated virtual environments make it possible to by-pass many of the problems related to low-level sensing and acting in the real world that are far removed from the cognitive aspects of intelligence, while preserving the need for intelligent real-time decision-making and interaction.

Expressive AI: Games and Artificial Intelligence

TLDR
It is argued that AIbased art and entertainment constitutes a new interdisciplinary agenda linking games studies, design practice, and technical research, and is called expressive AI.

Towards more human-like computer opponents

TLDR
Several play-critical differences between human and computer performance are identified, and a prototyping tool for constructing appropriately humanlike software agents is discussed.

Evolving opponents for interesting interactive computer games

TLDR
An evolutionary mechanism for opponents that keep learning from a player while playing against it while on-line is presented and its efficiency and robustness in increasing and maintaining the game’s interest are demonstrated.

Learning and Evaluating Human-Like NPC Behaviors in Dynamic Games

TLDR
This paper focuses on emulating human behaviors in strategic game settings, and focuses on a Social Ultimatum Game as the testbed for developing and evaluating a set of metrics for comparing various autonomous agents to human behavior collected from live experiments.

Review: Intelligent Agents for Computer Games

TLDR
Which approaches and fields of research are relevant to achieve a sophisticated goal-directed behavior for modern computer games' nonplayer characters are discussed and a classification of approaches for autonomous agents are presented.

Intelligent Agents for Computer Games

TLDR
Which approaches and fields of research are relevant to achieve a sophisticated goal-directed behavior for modern computer games’ nonplayer characters are discussed and a classification of approaches for autonomous agents are presented.

New Challenges for Character-Based AI for Games

TLDR
It is believed that character-based AI systems can draw from and contribute to the state of the art in such areas as pattern recognition and planning.
...