论文标题
卷曲：对比度无监督的表示，用于加强学习
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
论文作者
论文摘要
我们提出卷曲：对对比度无监督的表示，用于增强学习。 Curl使用对比度学习从原始像素中提取高级特征，并在提取功能的顶部进行范围内的控制。在DeepMind Control Suite和Atari游戏中，curl优于基于模型和模型的基于模型和模型的基于像素的方法，分别在100k环境和交互步骤中显示1.9倍和1.2倍的性能提升。在DeepMind Control Suite上，Curl是第一个基于图像的算法几乎匹配使用基于状态特征的方法的样品效率。我们的代码是开源的，可在https://github.com/mishalaskin/curl上找到。
We present CURL: Contrastive Unsupervised Representations for Reinforcement Learning. CURL extracts high-level features from raw pixels using contrastive learning and performs off-policy control on top of the extracted features. CURL outperforms prior pixel-based methods, both model-based and model-free, on complex tasks in the DeepMind Control Suite and Atari Games showing 1.9x and 1.2x performance gains at the 100K environment and interaction steps benchmarks respectively. On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features. Our code is open-sourced and available at https://github.com/MishaLaskin/curl.
