Distributed Service Area Control for Ride Sharing by using Multi-Agent Deep Reinforcement Learning.
Naoki YoshidaItsuki NodaToshiharu SugawaraPublished in: ICAART (1) (2021)
Keyphrases
- multi agent
- reinforcement learning
- control problems
- distributed control
- optimal control
- cooperative
- multiagent systems
- multi agent systems
- function approximation
- control policy
- web services
- learning agents
- intelligent agents
- control system
- markov decision processes
- loosely coupled
- action selection
- service providers
- end users
- autonomous agents
- control strategies
- adaptive control
- multi agent coordination
- multi agent architecture
- service oriented
- distributed environment
- software agents
- fully distributed
- robotic systems
- robot control
- management system
- single agent
- grid services
- mission critical
- computing environments
- control strategy
- state space
- blackboard architecture
- multi agent environments
- dynamic programming
- traffic signal control