On the Robustness of Controlled Deep Reinforcement Learning for Slice Placement.
José Jurandir Alves EstevesAmina BoubendirFabrice GuilleminPierre SensPublished in: J. Netw. Syst. Manag. (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- neural network
- temporal difference learning
- reinforcement learning algorithms
- model free
- markov decision processes
- multi agent reinforcement learning
- data sets
- action space
- learning classifier systems
- optimal policy
- digital images
- dynamic programming
- artificial neural networks
- image sequences
- decision trees
- social networks
- artificial intelligence
- databases