Scalable Deep Reinforcement Learning for Ride-Hailing.
Jiekun FengMark O. GluzmanJim G. DaiPublished in: IEEE Control. Syst. Lett. (2021)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- function approximation
- machine learning
- robotic control
- state space
- web scale
- memory efficient
- multi agent
- learning process
- model free
- direct policy search
- control problems
- highly scalable
- optimal policy
- learning algorithm
- transfer learning
- temporal difference
- lightweight
- supervised learning
- search engine
- artificial intelligence
- multi agent reinforcement learning
- data mining