CIRL: Controllable Imitative Reinforcement Learning for Vision-based Self-driving.
Xiaodan LiangTairui WangLuona YangEric P. XingPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- driver assistance systems
- intelligent vehicles
- function approximation
- vision system
- augmented reality
- human computer interaction
- driver assistance
- model free
- dynamic programming
- markov decision processes
- reinforcement learning algorithms
- learning algorithm
- real time
- computer vision
- learning problems
- temporal difference
- robotic control
- optimal control
- optimal policy
- supervised learning
- learning process
- machine learning
- neural network
- state space
- learning capabilities
- action space
- temporal difference learning
- computer controlled
- information systems
- policy search
- autonomous driving
- data sets