Multi-agent Service Area Adaptation for Ride-Sharing Using Deep Reinforcement Learning.
Naoki YoshidaItsuki NodaToshiharu SugawaraPublished in: PAAMS (2020)
Keyphrases
- reinforcement learning
- multi agent
- multi agent systems
- multi agent environments
- adaptation process
- function approximation
- multi agent reinforcement learning
- state space
- markov decision processes
- learning algorithm
- information services
- service oriented
- management system
- model free
- intelligent agents
- machine learning
- web services
- learning agents
- learning capabilities
- temporal difference
- service quality
- dynamic programming
- autonomous agents
- multiagent systems
- cooperative
- service discovery
- coalition formation
- software agents
- supervised learning
- single server
- partial observability
- multimedia
- heterogeneous agents
- team formation
- service providers