Scalable Deep Reinforcement Learning for Ride-Hailing.
Jiekun FengMark O. GluzmanJim G. DaiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- highly scalable
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- markov decision processes
- learning process
- model free
- multi agent
- supervised learning
- real time
- hidden markov models
- artificial neural networks
- partially observable
- information systems
- markov decision process
- deep learning
- multi agent reinforcement learning
- scale poorly