Adaptive Function Placement with Distributed Deep Reinforcement Learning in RAN Slicing.
Yu TsukamotoHaruhisa HirayamaSeung Il MoonHiroyuki ShinboPublished in: VTC Spring (2022)
Keyphrases
- reinforcement learning
- multi agent
- function approximators
- distributed systems
- distributed environment
- markov decision processes
- cooperative
- learning capabilities
- function approximation
- data sets
- model free
- fault tolerant
- state space
- learning algorithm
- least squares
- evolutionary algorithm
- communication cost
- temporal difference
- neural network
- database
- control policy
- distributed network
- policy search