Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Beyond Following: Mixing Active Initiative into Computational Creativity

Zhiyu Lin, Upol Ehsan, Rohan Agarwal, Samihan Dani, Vidushi Vashishth, Mark Riedl

TL;DR

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, indicating a robust association between effective MI-CC collaborative interactions, particularly the implementation of proactive AI initiatives, and deepened understanding among all participants.

Abstract

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.

Beyond Following: Mixing Active Initiative into Computational Creativity

TL;DR

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, indicating a robust association between effective MI-CC collaborative interactions, particularly the implementation of proactive AI initiatives, and deepened understanding among all participants.

Abstract

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.
Paper Structure (33 sections, 2 equations, 4 figures, 1 table)

This paper contains 33 sections, 2 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Study Design
  4. Task Setup
  5. The Delegation Setup.
  6. Domain chosen: Storytelling.
  7. Experimental AI System overview
  8. Creative Context
  9. Communications
  10. Experience Manager and Frontend
  11. Human Initiative.
  12. Agent Initiative.
  13. Learning from human.
  14. Study Methodology
  15. Pre-study.
  16. ...and 18 more sections

Figures (4)

  • Figure 1: Our system in action. How should an AI learn and adapt to the creators in this Mixed-Initiative Co-Creative setting?
  • Figure 2: One round of interaction of our experimental system. Each participant will experience multiple turns per session.
  • Figure 3: Participants' experience during the study.
  • Figure 4: Oracle experiment results on MAB algorithms of the agents performing on various feedback accuracy levels. Upper Bound performance, where the liked arm is always pulled, and the Lower Bound, where one not-liked arm is always pulled, is also presented for reference.