Safe Multi-Agent Deep Reinforcement Learning for Dynamic Virtual Network Allocation.
Akito SuzukiShigeaki HaradaPublished in: GLOBECOM (2020)
Keyphrases
- reinforcement learning
- multi agent
- dynamic networks
- multi agent reinforcement learning
- dynamic environments
- cooperative
- network model
- state space
- augmented reality
- virtual world
- complex networks
- network structure
- intelligent agents
- single agent
- allocation scheme
- network traffic
- autonomous agents
- multiagent systems
- peer to peer
- multi agent environments
- limited capacity
- multi agent systems
- neural network
- leader follower
- learning agents
- traffic signal
- team formation
- partially observable markov decision processes
- network management
- function approximation
- communication networks
- computer networks
- virtual reality
- dynamic programming
- learning process
- machine learning