# Counter-Strike Deathmatch with Large-Scale Behavioural Cloning

Source: [Counter-Strike Deathmatch with Large-Scale Behavioural Cloning](<https://www.sota2.com/research/paper/68fa6b601e209131cea2dd57>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:47:07.195Z

Authors: Tim Pearce, Jun Zhu

Published: 2021-04-09T09:12:12.000Z

## Abstract

This paper describes an AI agent that plays the popular first-person-shooter (FPS) video game \`Counter-Strike; Global Offensive' (CSGO) from pixel input. The agent, a deep neural network, matches the performance of the medium difficulty built-in AI on the deathmatch game mode, whilst adopting a humanlike play style. Unlike much prior work in games, no API is available for CSGO, so algorithms must train and run in real-time. This limits the quantity of on-policy data that can be generated, precluding many reinforcement learning algorithms. Our solution uses behavioural cloning - training on a large noisy dataset scraped from human play on online servers (4 million frames, comparable in size to ImageNet), and a smaller dataset of high-quality expert demonstrations. This scale is an order of magnitude larger than prior work on imitation learning in FPS games.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.04258>)

[PDF](<https://arxiv.org/pdf/2104.04258.pdf>)