Summary of Learning to Beat Byterl: Exploitability Of Collectible Card Game Agents, by Radovan Haluska et al.
Learning to Beat ByteRL: Exploitability of Collectible Card Game Agents
by Radovan Haluska, Martin Schmid
First submitted to arxiv on: 25 Apr 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 challenges of developing artificial agents for collectible card games, specifically Hearthstone and Legends of Code and Magic. While poker has been extensively studied, collectible card games pose unique difficulties due to their vast state spaces, making traditional search methods intractable. The authors present preliminary analysis results of ByteRL, a state-of-the-art agent that outperformed a top-10 Hearthstone player from China. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this game, artificial agents must work with imperfect information and make decisions quickly. While some agents are very good at playing games like poker, they struggle when the possible moves become too many to count. The authors looked at how well ByteRL did in Legends of Code and Magic and found that it can be beaten by a clever player. |
