论文标题
测量像素连续控制中的视觉概括
Measuring Visual Generalization in Continuous Control from Pixels
论文作者
论文摘要
自我监督的学习和数据增强已大大减少了持续控制任务中状态和基于图像的强化学习代理之间的性能差距。但是，目前尚不清楚当前的技术是否可以面对现实世界环境所需的各种视觉条件。我们提出了一个具有挑战性的基准测试，该基准通过在现有的连续控制域中添加图形变化来测试代理的视觉概括。我们的经验分析表明，当前的方法很难跨越各种视觉变化，我们研究了使这些任务困难的变异因素。我们发现，数据增强技术的表现优于自我监督的学习方法，并且更重要的图像转换提供了更好的视觉概括\脚注{基准和我们的增强actor-Critic-critic-critic实现是开放的 @ https:/ https://github.com/qithub.com/qdata/qdata/qdata/dmc_remastered）
Self-supervised learning and data augmentation have significantly reduced the performance gap between state and image-based reinforcement learning agents in continuous control tasks. However, it is still unclear whether current techniques can face a variety of visual conditions required by real-world environments. We propose a challenging benchmark that tests agents' visual generalization by adding graphical variety to existing continuous control domains. Our empirical analysis shows that current methods struggle to generalize across a diverse set of visual changes, and we examine the specific factors of variation that make these tasks difficult. We find that data augmentation techniques outperform self-supervised learning approaches and that more significant image transformations provide better visual generalization \footnote{The benchmark and our augmented actor-critic implementation are open-sourced @ https://github.com/QData/dmc_remastered)
