Learning to Move Like Professional Counter-Strike Players

TL;DR

This paper presents a data-driven, transformer-based model trained on professional CS:GO gameplay to generate human-like team movement, outperforming existing bots in realism and teamwork, with real-time efficiency suitable for commercial use.

Contribution

It introduces a scalable, efficient movement prediction model trained on professional gameplay data that produces human-like team coordination in CS:GO.

Findings

Model behaves more human-like than existing bots (16-59% higher TrueSkill rating).

Model performs basic teamwork and reduces movement mistakes.

Generated movement closely matches professional match statistics.

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.