Boosting human‐level AI with videogames: Mad University

2009

1 Abstract In our earlier research, we looked into the need for and use of AI in video games. Our survey on the existing literature on game artificial intelligence and our hands-on experience with some of the games which were developed through 1990s up to today have shown that the Artificial Intelligence in commercially available video games has made significant progress over the decades, but one area which commercial games have largely ignored is the use of learning AI. Meanwhile, game artificial intelligence research continues to look into and create examples of using such artificial intelligence techniques, e.g. reinforcement learning, evolutionary algorithms, in academic games. At the moment these techniques are largely employed only by game artificial intelligence research; however, considering that game environments in commercial games are becoming more dynamic and unpredictable, one would think that these techniques will be more capable of handling such environments and as su...

The incorporation of learning into commercial games can enrich the player experience, but may concern developers in terms of issues such as losing control of their game world. We explore a number of applied research and some fielded applications that point to the tremendous possibilities of machine learning research including game genres such as real-time strategy games, flight simulation games, car and motorcycle racing games, board games such as Go, an even traditional game-theoretic problems such as the prisoners dilemma. A common trait of these works is the potential of machine learning to reduce the burden of game developers. However a number of challenges exists that hinder the use of machine learning more broadly. We discuss some of these challenges while at the same time exploring opportunities for a wide use of machine learning in games.

2021

This work will explore three methods of machine learning that make it possible to train an algorithm to the extent that it can play the video game Super Mario and outperform human players. The aim is to find out which method of machine learning is best suited and what the differences are.

Communications of the ACM, 2002

Artificial Intelligence Review, 2008

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.

Is it possible to develop a computer program that can learn to play different video games by itself depending on the interactions with other players? Can video game characters learn new skills through interacting with human players? Can we make video games more interesting by allowing in-game characters to behave according to human player's strategy? These are just some of the questions that video game developers and artificial intelligence researchers are working on. In this paper we present an evolutionary approach that uses a modified particle swarm optimization algorithm and artificial neural networks, to answer these questions by allowing the agents to respond to changes in their surroundings. Video games usually require intelligent agents to adapt to new challenges and optimize their own utility with limited resources and our approach utilizes adaptive intelligence to improve an agent's game playing strategies. This research is directly applicable to video games research and evolutionary gaming. The approach presented here can be further extended to develop intelligent systems for the exploitation of weaknesses in an evolutionary system.

Computer, 2001

Building agents that can survive the harsh environment of a popular computer game provides fresh insight into the study of artificial intelligence.

Videogame Sciences and Arts, VJ 2023, 2024

We present an exploratory study comparing human player performance against online and offline AI learning techniques-the Naive Bayes Classifier and Genetic Algorithms, respectively-using a simple turn-based game. Human player performance is also assessed according to gender, age, experience playing games, and boredom level during game sessions. Human players and AI techniques are shown to obtain statistically equivalent score distributions. No gender performance differences were found, although performance seems to decrease with age. To a lesser extent, performance appears to improve with self-assessed experience and boredom levels. This study offers a base for more comprehensive experiments, suggesting various directions for future research.

This paper presents how artificial intelligence (AI) is used in computer games to solve common problems and provide game features. Specifically, non-playing character (NPC) path finding, decision making and learning are examined. Different AI techniques are looked at as to how they help provide a solution to these problems and features in computer games. This discussion is followed by a survey of research articles regarding the different type of AI techniques presented.

2001

understand what is required for human-level artificial intelligence. A key component of our methodology is developing AI systems that behave in complex, dynamic environments with many of the properties of the world we inhabit. Although robotics might seem an obvious choice, research in robotics requires solving many difficult problems related to low-level sensing and acting in the real world far removed from the cognitive aspects of intelligence. Simulated virtual environments make it possible to bypass many of these problems, while preserving the need for intelligent real-time decision-making and interaction. Unfortunately, development of realistic virtual environments is an expensive and time-consuming enterprise onto itself and requires expertise in many areas far afield from artificial intelligence. However, computer games provide us with a source of cheap, reliable, and flexible technology for developing our own virtual environments for research. Over the last four years, we ha...