Summary of Reinforcing Competitive Multi-agents For Playing So Long Sucker, by Medant Sharan et al.
Reinforcing Competitive Multi-Agents for Playing So Long Sucker
by Medant Sharan, Chandranath Adak
First submitted to arxiv on: 17 Nov 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 In this paper, researchers explore the application of classical deep reinforcement learning (DRL) algorithms, including DQN, DDQN, and Dueling DQN, in the strategy game So Long Sucker (SLS). The authors develop a novel implementation of SLS with a graphical user interface (GUI) and benchmarking tools for DRL algorithms. They demonstrate that while considered basic by modern standards, these classical DRL agents achieve roughly 50% of the maximum possible game reward after extensive training. However, agents occasionally make illegal moves, highlighting both the potential and limitations of these methods in semi-complex, socially driven games. The findings establish a foundational benchmark for training agents in SLS and similar negotiation-based environments, underscoring the need for advanced or hybrid DRL approaches to improve learning efficiency and adaptability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this study, researchers teach computers how to play a game called So Long Sucker. This game is special because it’s like two people working together, but also trying to trick each other. The scientists use old computer learning methods to try and get the computers to learn how to play the game well. They found that the computers can learn some things about the game, but they need to practice a lot and sometimes make mistakes. This study helps us understand how computers can learn from playing games like this one. |
Keywords
» Artificial intelligence » Reinforcement learning
