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

arXiv: https://arxiv.org/abs/2101.06220 · HTML: https://mlsanity.com/paper/2101.06220/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 140 references that are in the map.
- First posted on arXiv 15 Jan 2021.

## Builds on (most cited first, 8 of 8)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- ['It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisions](https://mlsanity.com/paper/1801.10408/) (2018)
- [Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators](https://mlsanity.com/paper/1901.06417/) (2019)
- [Neuroevolution in Games: State of the Art and Open Challenges](https://mlsanity.com/paper/1410.7326/) (2014)
- [From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI](https://mlsanity.com/paper/2002.10433/) (2020)
- [PCG-Based Game Design Patterns](https://mlsanity.com/paper/1610.03138/) (2016)
- [A Game-Based Approach for Helping Designers Learn Machine Learning Concepts](https://mlsanity.com/paper/2009.05605/) (2020)

## Built on by (most cited first, 8 of 8)

- [Unbounded: A Generative Infinite Game of Character Life Simulation](https://mlsanity.com/paper/2410.18975/) (2024)
- [Interrogating AI: Characterizing Emergent Playful Interactions with ChatGPT](https://mlsanity.com/paper/2401.08405/) (2024)
- [LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents](https://mlsanity.com/paper/2410.02829/) (2024)
- [Design-Driven Requirements for Computationally Co-Creative Game AI Design Tools](https://mlsanity.com/paper/2107.13738/) (2021)
- [Improving Fairness in Adaptive Social Exergames via Shapley Bandits](https://mlsanity.com/paper/2302.09298/) (2023)
- [Dealing with Adversarial Player Strategies in the Neural Network Game iNNk through Ensemble Learning](https://mlsanity.com/paper/2107.02052/) (2021)
- [AI-Gadget Kit: Integrating Swarm User Interfaces with LLM-driven Agents for Rich Tabletop Game Applications](https://mlsanity.com/paper/2407.17086/) (2024)
- [DiVA: Enabling Interactive Digital Life Simulation via Video Models](https://mlsanity.com/paper/2609.13830/) (2026)

## Abstract (arXiv)

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 interaction in the context of AI-infused systems. Our core finding is that AI as play can expand current notions of human-AI interaction, which are predominantly productivity-based. In particular, our work suggests that game and UX designers should consider flow to structure the learning curve of human-AI interaction, incorporate discovery-based learning to play around with the AI and observe the consequences, and offer users an invitation to play to explore new forms of human-AI interaction.