Counter-Strike Deathmatch with Large-Scale Behavioural Cloning
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.
Keywords
Cite
@article{arxiv.2104.04258,
title = {Counter-Strike Deathmatch with Large-Scale Behavioural Cloning},
author = {Tim Pearce and Jun Zhu},
journal= {arXiv preprint arXiv:2104.04258},
year = {2021}
}
Comments
Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2021