Spatio-temporal Incentives Optimization for Ride-hailing Services with Offline Deep Reinforcement Learning.
Yanqiu WuQingyang LiZhiwei Tony QinPublished in: CoRR (2022)
Keyphrases
- spatio temporal
- reinforcement learning
- spatial and temporal
- information services
- end users
- context aware
- state space
- global optimization
- function approximation
- space time
- optimization algorithm
- optimization process
- optimization problems
- image sequences
- user centric
- real time
- optimization model
- multi agent
- web services
- service oriented
- learning algorithm
- model free
- service providers
- dynamic programming
- learning problems
- optimization method
- markov decision processes
- moving objects
- multimedia
- action selection