Summary of Automating Creativity, by Ming-hui Huang et al.
Automating Creativity
by Ming-Hui Huang, Roland T. Rust
First submitted to arxiv on: 11 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper aims to bridge the gap between generative and creative AI by developing a triple prompt-response-reward engineering framework. The proposed approach combines reinforcement learning with computational creativity research streams to foster creativity in Generative AI (GenAI). The framework consists of three components: a prompt model for expected creativity, a response model for observed creativity, and a reward model for improving creativity over time. This innovative framework enables GenAI applications at various levels of creativity strategically. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper tries to make artificial intelligence (AI) more creative by using a special kind of learning called reinforcement learning. The goal is to make AI that can come up with new and interesting ideas, not just repeat what it’s been taught. To do this, the researchers created a system with three parts: one for creating prompts, one for generating responses, and one for giving feedback on how creative those responses are. This system could be used to make AI that can help with things like writing stories or composing music. |
Keywords
» Artificial intelligence » Prompt » Reinforcement learning
