Summary of Learning to Move Like Professional Counter-strike Players, by David Durst et al.
Learning to Move Like Professional Counter-Strike Players
by David Durst, Feng Xie, Vishnu Sarukkai, Brennan Shacklett, Iuri Frosio, Chen Tessler, Joohwan Kim, Carly Taylor, Gilbert Bernstein, Sanjiban Choudhury, Pat Hanrahan, Kayvon Fatahalian
First submitted to arxiv on: 25 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR)
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 The proposed research demonstrates a data-driven approach to creating human-like movement controllers for multiplayer first-person shooter games like Counter-Strike: Global Offensive (CS:GO). By training a transformer-based movement model using a dataset comprising 123 hours of professional game play traces, the authors generate team movement that mimics human behavior. The efficient inference time of less than 0.5 ms per game step makes it feasible for commercial use. Evaluations by human assessors show that the model outperforms commercially available bots and procedural controllers in terms of TrueSkill rating of “human-like” (16% to 59%). Experiments involving bot self-play demonstrate simple forms of teamwork, reduced movement mistakes, and similar movement distributions, player lifetimes, and kill locations compared to professional CS:GO match play. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The researchers created a system that helps players move around in the popular game Counter-Strike: Global Offensive (CS:GO) like real people do. They used data from 123 hours of pro games to train a computer model that can predict how teams will move during gameplay. This model is fast and efficient, taking less than half a millisecond per step. People who played the game with this AI system said it was more realistic and made better decisions than other types of computer-controlled players. |
Keywords
» Artificial intelligence » Inference » Transformer
