Deep Reinforcement Learning for Ride-sharing Dispatching and Repositioning.
Zhiwei (Tony) QinXiaocheng TangYan JiaoFan ZhangChenxi WangQun (Tracy) LiPublished in: IJCAI (2019)
Keyphrases
- reinforcement learning
- scheduling problem
- function approximation
- robotic control
- reinforcement learning algorithms
- learning algorithm
- relational reinforcement learning
- state space
- optimal policy
- markov decision processes
- learning capabilities
- temporal difference
- model free
- direct policy search
- production scheduling
- control problems
- supervised learning
- learning process
- multi agent
- neural network
- data sets
- markov decision process
- deep learning
- stochastic approximation
- policy search
- real world