Rebalancing the car-sharing system with reinforcement learning.
Changwei RenLixingjian AnZhanquan GuYuexuan WangYunjun GaoPublished in: World Wide Web (2020)
Keyphrases
- reinforcement learning
- function approximation
- search tree
- information sharing
- real time
- knowledge sharing
- markov decision processes
- reinforcement learning algorithms
- state space
- learning process
- binary search trees
- data sharing
- function approximators
- temporal difference
- temporal difference learning
- multi agent reinforcement learning
- real world
- model free
- dynamic programming
- multi agent
- machine learning
- optimal control
- optimal policy
- least squares
- partially observable
- share information
- evolutionary algorithm
- robotic control