Deep Reinforcement Learning-based Trajectory Pricing on Ride-hailing Platforms.
Jianbin HuangLongji HuangMeijuan LiuHe LiQinglin TanXiaoke MaJiangtao CuiDe-Shuang HuangPublished in: ACM Trans. Intell. Syst. Technol. (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model free
- profit maximization
- multi agent reinforcement learning
- trajectory data
- machine learning
- optimal control
- learning process
- optimal policy
- markov decision processes
- distributional assumptions
- dynamic programming
- reinforcement learning algorithms
- mechanism design
- pricing model
- multi agent
- deep learning
- temporal difference
- autonomous learning
- software platform
- action space
- robot control
- computing platform
- supervised learning
- learning algorithm