arXiv 2104.042582021-04cs.AIcs.LGstat.ML

大规模行为克隆反恐精英死亡竞赛

Counter-Strike Deathmatch with Large-Scale Behavioural Cloning

Tsinghua University（清华大学）；University of Cambridge（剑桥大学）

Tim Pearce, Jun Zhu

备注：: Offline Reinforcement Learning Workshop at Neural Information Processing Systems, 2021

摘要：

本文描述了一个人工智能智能体，玩流行的第一人称射击（FPS）视频游戏“反恐精英;全球攻势”（CSGO）从像素输入。该代理是一个深度神经网络，在死亡竞赛游戏模式下与中等难度内置AI的性能相匹配，同时采用类似人类的游戏风格。与游戏中的许多先前工作不同，CSGO没有可用的API，因此算法必须实时训练和运行。这限制了可以生成的策略数据的数量，排除了许多强化学习算法。我们的解决方案使用行为克隆-在从在线服务器上的人类游戏中抓取的大型噪声数据集（400万帧，大小与ImageNet相当）和高质量专家演示的较小数据集上进行训练。这个规模比先前在FPS游戏中的模仿学习工作大一个数量级。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。