Imitative Reinforcement Learning Fusing Vision and Pure Pursuit for Self-driving.
Mingxing PengZhihao GongChen SunLong ChenDongpu CaoPublished in: ICRA (2020)
Keyphrases
- reinforcement learning
- computer vision
- function approximation
- vision system
- markov decision processes
- model free
- reinforcement learning algorithms
- temporal difference
- learning process
- optimal policy
- learning capabilities
- visual perception
- state space
- multi agent reinforcement learning
- learning algorithm
- real time
- monte carlo
- temporal difference learning
- active vision
- relational reinforcement learning
- action selection
- dynamic programming
- hidden markov models
- data sets