Where to go: Agent Guidance with Deep Reinforcement Learning in A City-Scale Online Ride-Hailing Service.
Jiyao LiVicki H. AllanPublished in: ITSC (2022)
Keyphrases
- reinforcement learning
- multi agent
- multi agent systems
- online learning
- learning agent
- action selection
- intelligent agents
- function approximation
- software agents
- agent architecture
- multiagent systems
- online services
- initially unknown
- autonomous learning
- web services
- dynamic environments
- decision making
- partially observable
- multiple agents
- service providers
- markov decision process
- single agent
- learning capabilities
- reinforcement learning algorithms
- public transportation
- learning agents
- multiagent reinforcement learning
- state action
- exploration strategy
- public transport
- agent model
- information services
- markov decision processes
- autonomous agents
- state space
- agent learns
- multi agent environments
- robocup soccer
- agent receives
- balancing exploration and exploitation
- state abstraction
- function approximators
- action space
- reward function
- service quality
- mobile agents
- e government