CURL: Contrastive Unsupervised Representations for Reinforcement Learning
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
复制标题
DOI：
--
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
A. Srinivas;M. Laskin;P. Abbeel
中科院分区：
文献类型：
--
作者：
A. Srinivas;M. Laskin;P. Abbeel
我们提出了强化学习的CURL：对比无监督表示法。CURL使用对比学习从原始像素中提取高层特征，并在提取的特征上执行非策略控制。在DeepMind Control Suite和Atari Games中的复杂任务上，Curl的表现优于之前基于像素的方法，无论是基于模型的方法还是非模型的方法，在100K环境和交互步骤基准下分别获得1.9倍和1.2倍的性能提升。在DeepMind Control Suite上，CURL是第一个几乎与使用基于状态的特征的方法的采样效率相媲美的基于图像的算法。我们的代码是开源的，可从以下的HTTPS URL获得。
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 this https URL.