Summary of Enhancements For Real-time Monte-carlo Tree Search in General Video Game Playing, by Dennis J.n.j. Soemers and Chiara F. Sironi and Torsten Schuster and Mark H.m. Winands
Enhancements for Real-Time Monte-Carlo Tree Search in General Video Game Playing
by Dennis J.N.J. Soemers, Chiara F. Sironi, Torsten Schuster, Mark H.M. Winands
First submitted to arxiv on: 3 Jul 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 presents eight enhancements for Monte-Carlo Tree Search (MCTS), a search technique used in General Video Game Playing (GVGP). GVGP involves agents playing various real-time video games without prior knowledge of the game. The enhancements, some known and others novel, are designed to improve MCTS’s performance in GVGP. These include Progressive History, N-Gram Selection Technique, Tree Reuse, Breadth-First Tree Initialization, Loss Avoidance, Novelty-Based Pruning, Knowledge-Based Evaluations, and Deterministic Game Detection. Each enhancement is shown to provide statistically significant increases in win percentages when applied individually. When combined, they significantly boost the average win percentage over 60 different games from 31.0% to 48.4%, approaching the level of competitive agents like those in the GVG-AI competition in 2015. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research is about making computer programs better at playing video games without knowing which game they’ll play ahead of time. The program uses a special technique called Monte-Carlo Tree Search to make decisions during gameplay. To improve this technique, the researchers came up with eight new ideas. Some of these ideas are already known, but some are brand new. When tested individually, each idea helped the program win more games. When all eight ideas were used together, the program won significantly more games than before – it was almost as good as the best programs that played in a big video game competition. |
Keywords
» Artificial intelligence » N gram » Pruning
