End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning.
Alessandro Paolo CapassoPaolo MaramottiAnthony Dell'EvaAlberto BroggiPublished in: IV (2021)
Keyphrases
- end to end
- reinforcement learning
- multi agent
- admission control
- congestion control
- optimal policy
- markov decision processes
- wireless ad hoc networks
- ad hoc networks
- high bandwidth
- multi agent systems
- rate allocation
- intelligent agents
- multipath
- internet protocol
- text localization and recognition
- learning algorithm
- content delivery
- multi hop
- video sequences
- image sequences