Cooperative cache update using multi-agent recurrent deep reinforcement learning for mobile edge networks.
Manoj Kumar SomesulaRashmi Ranjan RoutDurvasula V. L. N. SomayajuluPublished in: Comput. Networks (2022)
Keyphrases
- multi agent
- cooperative
- reinforcement learning
- cache invalidation
- multi agent systems
- proxy cache
- multi agent reinforcement learning
- multiagent systems
- markov decision processes
- social networks
- function approximation
- spiking neural networks
- network connectivity
- game theory
- mobile devices
- edge detection
- mobile phone
- state space
- agent based simulations
- mobile computing
- mobile environments
- multiple agents
- cooperative agents
- dynamic programming
- multimedia services
- learning agents
- single agent
- temporal difference
- edge information
- weighted graph
- delay tolerant
- computing environments
- feed forward
- data access
- network structure
- machine learning
- multi agent environments
- autonomous agents
- recurrent networks
- mobile clients
- mobile users
- neural network
- optimal policy