Summary of Dominion: a New Frontier For Ai Research, by Danny Halawi et al.
Dominion: A New Frontier for AI Research
by Danny Halawi, Aron Sarmasi, Siena Saltzen, Joshua McCoy
First submitted to arxiv on: 10 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 explores the application of reinforcement learning (RL) algorithms in the tabletop game Dominion, a popular strategy game. By analyzing the properties of Dominion, the authors identify its suitability as a benchmark for evaluating the next generation of RL models. To facilitate this evaluation, they present the Dominion Online Dataset, comprising over 2 million games played by experienced players. The paper also introduces an RL baseline bot that uses existing techniques to outperform common heuristic-based bots and demonstrates competitive performance against the previously strongest bot. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about using artificial intelligence (AI) to play a popular board game called Dominion. Right now, AI can beat humans in some games like chess or video games, but it’s not perfect yet. The authors of this paper want to improve AI by playing Dominion and seeing how well they do compared to human players. They created a big dataset with millions of games played online and then used this data to train an AI bot that can play Dominion better than some other bots. This is important because it helps us understand how AI works and how we can make it even smarter in the future. |
Keywords
» Artificial intelligence » Reinforcement learning
