Deep Reinforcement Learning for Multi-driver Vehicle Dispatching and Repositioning Problem.
John HollerRisto VuorioZhiwei (Tony) QinXiaocheng TangYan JiaoTiancheng JinSatinder SinghChenxi WangJieping YePublished in: ICDM (2019)
Keyphrases
- reinforcement learning
- traffic accidents
- dangerous situations
- driver assistance systems
- intelligent vehicles
- road safety
- function approximation
- real time
- state space
- scheduling problem
- vehicle speed
- pedestrian detection
- autonomous vehicles
- advanced driver assistance systems
- production scheduling
- deep learning
- vehicle detection
- manufacturing systems
- learning process
- multi agent
- learning algorithm
- machine learning
- optimal control
- markov decision processes
- traffic management
- path planning
- computer controlled
- optimal policy
- neural network