Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service.
Jiyao LiVicki H. AllanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- action selection
- online services
- online learning
- real time
- multi agent systems
- multiagent systems
- learning agent
- reinforcement learning agents
- state space
- decision making
- multiple agents
- partially observable
- function approximation
- learning capabilities
- service providers
- intelligent agents
- autonomous learning
- management system
- learning algorithm
- exploration strategy
- information services
- agent receives
- multi agent environments
- cooperative
- web services
- reward function
- markov decision processes
- public transport
- model free
- mobile agents
- dynamic environments
- end users
- machine learning
- multiagent reinforcement learning
- balancing exploration and exploitation
- initially unknown
- state action
- function approximators
- action space
- single agent
- human users
- agent architecture
- service composition
- scale space