强化学习在计算机视觉领域的应用

目标跟踪：

1. Learning Policies for Adaptive Tracking with Deep Feature Cascades
   (ICCV 2017, Paper, Code)

视觉导航：

1. PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning
   (2017, Paper, Code)

2. Vision-based Navigation Using Deep Reinforcement Learning
   (2019, Paper, Code)

3. Learning to Learn how to Learn: Self-Adaptive Visual Navigation using Meta-Learning
   (CVPR 2019, Paper, Code)

4. Visual Navigation with Spatial Attention
   (CVPR 2021, Paper, Code)

点云配准：

1. ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning
   (CVPR 2021, Paper, Code)