# Learning to Move Like Professional Counter-Strike Players

arXiv: https://arxiv.org/abs/2408.13934 · HTML: https://mlsanity.com/paper/2408.13934/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 48 references that are in the map.
- First posted on arXiv 25 Aug 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting](https://mlsanity.com/paper/2103.14023/) (2021)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [MineRL: A Large-Scale Dataset of Minecraft Demonstrations](https://mlsanity.com/paper/1907.13440/) (2019)
- [MotionLM: Multi-Agent Motion Forecasting as Language Modeling](https://mlsanity.com/paper/2309.16534/) (2023)
- [Towards Learning a Generalist Model for Embodied Navigation](https://mlsanity.com/paper/2312.02010/) (2023)
- [Playing FPS Games with Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05521/) (2016)
- [Counter-Strike Deathmatch with Large-Scale Behavioural Cloning](https://mlsanity.com/paper/2104.04258/) (2021)
- [ADAPT: Efficient Multi-Agent Trajectory Prediction with Adaptation](https://mlsanity.com/paper/2307.14187/) (2023)
- [Benchmarking End-to-End Behavioural Cloning on Video Games](https://mlsanity.com/paper/2004.00981/) (2020)
- [ESTA: An Esports Trajectory and Action Dataset](https://mlsanity.com/paper/2209.09861/) (2022)

## Built on by (most cited first, 4 of 4)

- [X-Ego: Acquiring Team-Level Tactical Situational Awareness via Cross-Egocentric Contrastive Video Representation Learning](https://mlsanity.com/paper/2510.19150/) (2025)
- [A Data-Driven Discretized CS:GO Simulation Environment to Facilitate Strategic Multi-Agent Planning Research](https://mlsanity.com/paper/2509.06355/) (2025)
- [VLMs for Videogame Data Annotation](https://mlsanity.com/paper/2608.05949/) (2026)
- [Training a Conditioned Video Game Agent on a VLM Annotated Dataset](https://mlsanity.com/paper/2608.05954/) (2026)

## Abstract (arXiv)

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.