规模行为克隆提升因果推理：一个用于实时视频游戏播放的开放模型
Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
AI总结：
本研究提出了一种开放的训练方法，通过扩大模型和数据规模提升因果推理能力，展示了在实时视频游戏中的高性能表现。
摘要：
行为克隆在模型和数据规模扩大时表现出强劲的性能。在本工作中，我们提出了一种开放的训练配方，用于训练一个用于实时推理的视频游戏播放基础模型，该模型可在消费级GPU上运行。我们以开放许可发布了所有数据（8300多小时的高质量人类游戏录像）、训练和推理代码以及预训练检查点。实证研究表明，我们的最佳模型在各种3D游戏中表现出与人类玩家相当的性能。我们使用此配方研究行为克隆的扩展规律，重点在于因果推理。在受控的玩具设置中，我们首先证明增加训练数据和网络深度会使模型学习更因果的策略。然后我们验证了这些发现的扩展性，分析了高达12亿参数的模型。我们观察到在玩具领域观察到的因果改进在模型规模和训练步骤增加时仍然成立。
英文摘要：
Behavior cloning has seen a resurgence as scaling model and data sizes demonstrate strong performance. In this work, we introduce an open recipe for training a video game playing foundation model designed for inference in realtime on a consumer GPU. We release all data (8300+ hours of high quality human gameplay), training and inference code, and pretrained checkpoints under an open license. Empirically, we show that our best model achieves performance competitive with human players across a variety of 3D games. We use this recipe to investigate the scaling laws of behavior cloning, with a focus on causal reasoning. In a controlled toy setting, we first demonstrate that increasing training data and network depth leads to the model learning a more causal policy. We then validate these findings at scale, analyzing models up to 1.2 billion parameters. We observe that the causal improvements seen in the toy domain hold true as model size and training steps increase.
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。
