Player-AI Interaction: What Neural Network Games Reveal About AI as Play

@article{Zhu2021PlayerAIIW,
  title={Player-AI Interaction: What Neural Network Games Reveal About AI as Play},
  author={Jichen Zhu and Jennifer Villareale and Nithesh Javvaji and Sebastian Risi and Mathias L{\"o}we and Rush Weigelt and Casper Harteveld},
  journal={Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems},
  year={2021}
}
The advent of artificial intelligence (AI) and machine learning (ML) bring human-AI interaction to the forefront of HCI research. This paper argues that games are an ideal domain for studying and experimenting with how humans interact with AI. Through a systematic survey of neural network games (n = 38), we identified the dominant interaction metaphors and AI interaction patterns in these games. In addition, we applied existing human-AI interaction guidelines to further shed light on player-AI… 

Figures and Tables from this paper

Understanding Mental Models of AI through Player-AI Interaction
TLDR
It is presented the position that AI-based games, particularly the player-AI interaction component, offer an ideal domain to study the process in which mental models evolve, and a case study to illustrate the benefits of this approach for explainable AI.
Square peg, round hole: A case study on using Visual Question & Answering in Games
TLDR
This work considers the scenario of Visual Question & Answering (VQA) - the automatic answering of a textual question about an image and presents two original prototypes designed to explore the potential of VQA in games and discusses preliminary findings originated through a Wizard of Oz pilot study.
Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications 92-102
TLDR
This work proposes a preliminary framework to analyze co-creative GAN applications and identifies four primary interaction patterns: Curating, Exploring, Evolving, and Conditioning.
Design-Driven Requirements for Computationally Co-Creative Game AI Design Tools
TLDR
This work presents a participatory design study that categorizes and analyzes game AI designers’ workflows, goals, and expectations for co-creative tools, and presents implications for future co- Creativity tool research and development.
Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning
TLDR
This paper focuses on the adversarial player strategy aspect in the game iNNk, in which players try to communicate secret code words through drawings with the goal of not being deciphered by a NN, and presents a method that combines transfer learning and ensemble methods to obtain a data-efficient adaptation to these strategies.
From Flow to Fuse
TLDR
This work uses cognitive science theory to expose inconsistencies in flow's prevalent definition, and introduces fuse, a concept related to flow but consistent with cognitive science, and defined as the "fusion of activity-related sensory stimuli and awareness''.
“Rather Solve the Problem from Scratch”: Gamesploring Human-Machine Collaboration for Optimizing the Debris Collection Problem
TLDR
This paper developed a digital game where players can request the help of the computer while facing a multi-objective problem of assigning contractors to road segments for clearing debris in a disaster area and assessed how players optimized under various circumstances compared to the computer on its own.
For What It’s Worth: Humans Overwrite Their Economic Self-interest to Avoid Bargaining With AI Systems
As algorithms are increasingly augmenting and substituting human decision-making, understanding how the introduction of computational agents changes the fundamentals of human behavior becomes vital.
From Flow to Fuse: A Cognitive Perspective
TLDR
F fuse is introduced, a concept related to flow but consistent with cognitive science, and defined as the “fusion of activity-related sensory stimuli and awareness”, and a preliminary model is developed that hypothesizes fuse’s underlying cognitive processes.

References

SHOWING 1-10 OF 134 REFERENCES
Guidelines for Human-AI Interaction
TLDR
This work proposes 18 generally applicable design guidelines for human-AI interaction that can serve as a resource to practitioners working on the design of applications and features that harness AI technologies, and to researchers interested in the further development of human- AI interaction design principles.
AI-based Game Design Patterns
TLDR
A generative ideation technique to combine a design pattern with an AI technique or capacity to make newAI-based games is proposed and demonstrated through two examples of AI-based game prototypes created using these patterns.
Oui, Chef!!: Supervised Learning for Novel Gameplay with Believable AI
TLDR
The design and implementation of Oui, Chef!! is outlined, a supervised learning game in which the player trains neural networks to map recipes to the ingredients necessary to make dishes in a restaurant, demonstrating that training game agents in a supervised manner provides a fun and engaging player experience.
Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design
TLDR
This paper identifies two sources of AI's distinctive design challenges: 1) uncertainty surrounding AI's capabilities, 2) AI's output complexity, spanning from simple to adaptive complex, and 3) four levels of AI systems.
Mental Models of AI Agents in a Cooperative Game Setting
TLDR
It is proposed that understanding the underlying technology is insufficient for developing appropriate conceptual models for AI systems, and analysis of behavior is also necessary, and future work for studying the revision of mental models over time is suggested.
Getting Playful with Explainable AI: Games with a Purpose to Improve Human Understanding of AI
TLDR
This research offers a novel approach to assess how humans interpret AI explanations by integrating XAI with Games with a Purpose (GWAP), and demonstrates application through the creation of a multi-player GWAP that focuses on explaining deep learning models trained for image recognition.
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.
Game AI Pro 2: Collected Wisdom of Game AI Professionals
Game AI Pro2: Collected Wisdom of Game AI Professionals presents cutting-edge tips, tricks, and techniques for artificial intelligence (AI) in games, drawn from developers of shipped commercial games
Explainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation
TLDR
This vision paper proposes a new research area of eXplainable AI for Designers (XAID), specifically for game designers, and illustrates the initial XAID framework through three use cases, which require an understanding both of the innate properties of the AI techniques and users’ needs.
Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
TLDR
The design of the Morai Maker intelligent tool is discussed, which developed a game level design tool for Super Mario Bros.-style games with a built-in AI level designer and found that level designers vary in their desired interactions with, and role of, the AI.
...
1
2
3
4
5
...