Counter-Strike Deathmatch with Large-Scale Behavioural Cloning

TL;DR

This paper presents a deep neural network agent for Counter-Strike: Global Offensive that uses large-scale behavioural cloning from real human gameplay data to achieve humanlike performance without API access.

Contribution

The work introduces a large-scale behavioural cloning approach trained on extensive real-world gameplay data, enabling effective FPS game AI without API reliance.

Findings

Agent matches medium difficulty AI performance

Uses 4 million frames of human gameplay data

Achieves humanlike play style

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.