任务是地图里面导航，让agent从起始点到达指定位置。
用了supervised learning + reinforcement learning + lstm
用supervised learning当做辅助训练，加速rl训练，用lstm当做memory。实验表明depth construction比较有用。
LEARNING TO NAVIGATE IN COMPLEX ENVIRONMENTS
Posted tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了LEARNING TO NAVIGATE IN COMPLEX ENVIRONMENTS相关的知识，希望对你有一定的参考价值。
以上是关于LEARNING TO NAVIGATE IN COMPLEX ENVIRONMENTS的主要内容，如果未能解决你的问题，请参考以下文章
learning to see in the dark: 弱光场景下基于相机底层信号的图像处理
how-to-get-a-job-in-deep-learning
To discount or not to discount in reinforcement learning: A case study comparing R learning and Q le
Learning-to-See-in-the-Dark跑通及实现方法
Learning to Combat Compounding-Error in Model-Based Reinforcement Learning
（转）8 Tactics to Combat Imbalanced Classes in Your Machine Learning Dataset