Learning to Move Like Professional Counter-Strike Players
David Durst, Feng Xie, Vishnu Sarukkai, Brennan Shacklett, Iuri Frosio, Chen Tessler, Joohwan Kim, Carly Taylor, Gilbert Bernstein, Sanjiban Choudhury, Pat Hanrahan, Kayvon Fatahalian
2024-08-27
Summary
This paper discusses a new method for teaching computer programs to move like professional players in the game Counter-Strike: Global Offensive (CS:GO) by using data from real gameplay.
What's the problem?
In competitive games like CS:GO, how players move and work together is crucial for success. However, it’s difficult to create movement strategies for every possible situation in the game because there are so many different maps and scenarios. Traditional methods of programming these movements can be too complex and time-consuming.
What's the solution?
The authors collected a dataset of 123 hours of professional gameplay to train a model that can predict human-like movements for players during specific game rounds. They used a type of AI model called a transformer to learn from this data. The resulting movement model is very efficient, working quickly enough to be used in real-time during games. Tests showed that this model mimics human behavior better than existing game bots and scripted movements, making it more effective at teamwork and reducing common mistakes.
Why it matters?
This research is important because it helps improve how AI can control characters in video games, making them behave more like real players. This can enhance the gaming experience for players by providing smarter opponents or teammates, leading to more realistic and engaging gameplay.
Abstract
In multiplayer, first-person shooter games like Counter-Strike: Global Offensive (CS:GO), coordinated movement is a critical component of high-level strategic play. However, the complexity of team coordination and the variety of conditions present in popular game maps make it impractical to author hand-crafted movement policies for every scenario. We show that it is possible to take a data-driven approach to creating human-like movement controllers for CS:GO. We curate a team movement dataset comprising 123 hours of professional game play traces, and use this dataset to train a transformer-based movement model that generates human-like team movement for all players in a "Retakes" round of the game. Importantly, the movement prediction model is efficient. Performing inference for all players takes less than 0.5 ms per game step (amortized cost) on a single CPU core, making it plausible for use in commercial games today. Human evaluators assess that our model behaves more like humans than both commercially-available bots and procedural movement controllers scripted by experts (16% to 59% higher by TrueSkill rating of "human-like"). Using experiments involving in-game bot vs. bot self-play, we demonstrate that our model performs simple forms of teamwork, makes fewer common movement mistakes, and yields movement distributions, player lifetimes, and kill locations similar to those observed in professional CS:GO match play.