# Beyond Following: Mixing Active Initiative into Computational Creativity

arXiv: https://arxiv.org/abs/2409.16291 · HTML: https://mlsanity.com/paper/2409.16291/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 41 references that are in the map.
- First posted on arXiv 6 Sep 2024.

## Builds on (most cited first, 17 of 17)

- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [Deep Reinforcement Learning from Policy-Dependent Human Feedback](https://mlsanity.com/paper/1902.04257/) (2019)
- [Human-Centered Artificial Intelligence and Machine Learning](https://mlsanity.com/paper/1901.11184/) (2019)
- [Explainability Pitfalls: Beyond Dark Patterns in Explainable AI](https://mlsanity.com/paper/2109.12480/) (2021)
- [Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systems](https://mlsanity.com/paper/2305.07465/) (2023)
- [Co-Creative Level Design via Machine Learning](https://mlsanity.com/paper/1809.09420/) (2018)
- [NovGrid: A Flexible Grid World for Evaluating Agent Response to Novelty](https://mlsanity.com/paper/2203.12117/) (2022)
- [Creative Wand: A System to Study Effects of Communications in Co-Creative Settings](https://mlsanity.com/paper/2208.02886/) (2022)
- [Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds](https://mlsanity.com/paper/1709.03969/) (2017)
- [An Ontology of Co-Creative AI Systems](https://mlsanity.com/paper/2310.07472/) (2023)
- [Story Designer: Towards a Mixed-Initiative Tool to Create Narrative Structures](https://mlsanity.com/paper/2210.09294/) (2022)
- [Preference-Learning Emitters for Mixed-Initiative Quality-Diversity Algorithms](https://mlsanity.com/paper/2210.13839/) (2022)
- [Player Modeling via Multi-Armed Bandits](https://mlsanity.com/paper/2102.05264/) (2021)
- [Holding the Line: A Study of Writers' Attitudes on Co-creativity with AI](https://mlsanity.com/paper/2404.13165/) (2024)

## Abstract (arXiv)

Generative Artificial Intelligence (AI) encounters limitations in efficiency and fairness within the realm of Procedural Content Generation (PCG) when human creators solely drive and bear responsibility for the generative process. Alternative setups, such as Mixed-Initiative Co-Creative (MI-CC) systems, exhibited their promise. Still, the potential of an active mixed initiative, where AI takes a role beyond following, is understudied. This work investigates the influence of the adaptive ability of an active and learning AI agent on creators' expectancy of creative responsibilities in an MI-CC setting. We built and studied a system that employs reinforcement learning (RL) methods to learn the creative responsibility preferences of a human user during online interactions. Situated in story co-creation, we develop a Multi-armed-bandit agent that learns from the human creator, updates its collaborative decision-making belief, and switches between its capabilities during an MI-CC experience. With 39 participants joining a human subject study, Our developed system's learning capabilities are well recognized compared to the non-learning ablation, corresponding to a significant increase in overall satisfaction with the MI-CC experience. These findings indicate a robust association between effective MI-CC collaborative interactions, particularly the implementation of proactive AI initiatives, and deepened understanding among all participants.