论文标题
SWIN Transformers深入的强化学习
Deep Reinforcement Learning with Swin Transformers
论文作者
论文摘要
变形金刚是使用多层自我注意力头的神经网络模型，并且在自然语言处理任务中具有巨大的潜力。同时，已经努力使变形金刚适应机器学习的视觉任务，包括视觉变压器和SWIN变形金刚。尽管一些研究人员使用视觉变压器来加强学习任务，但由于高计算成本，他们的实验仍然很小。本文介绍了基于Swin Transformers：Swin DQN的第一个在线增强学习计划。与现有研究相反，我们的新颖方法证明了在街机学习环境中49场比赛中实验的出色表现。结果表明，在所有49场比赛中的45场（92％）中，我们的方法的最大评估得分明显高于基线方法，而平均评估得分高于所有49场比赛中的40场基线方法（82％）（82％）。
Transformers are neural network models that utilize multiple layers of self-attention heads and have exhibited enormous potential in natural language processing tasks. Meanwhile, there have been efforts to adapt transformers to visual tasks of machine learning, including Vision Transformers and Swin Transformers. Although some researchers use Vision Transformers for reinforcement learning tasks, their experiments remain at a small scale due to the high computational cost. This article presents the first online reinforcement learning scheme that is based on Swin Transformers: Swin DQN. In contrast to existing research, our novel approach demonstrate the superior performance with experiments on 49 games in the Arcade Learning Environment. The results show that our approach achieves significantly higher maximal evaluation scores than the baseline method in 45 of all the 49 games (92%), and higher mean evaluation scores than the baseline method in 40 of all the 49 games (82%).
