Controlled Deep Reinforcement Learning for Optimized Slice Placement.
José Jurandir Alves EstevesAmina BoubendirFabrice GuilleminPierre SensPublished in: MeditCom (2021)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- learning algorithm
- state space
- direct policy search
- real time
- robotic control
- stochastic approximation
- control problems
- reinforcement learning algorithms
- least squares
- machine learning
- transfer learning
- optimal control
- learning process
- deep learning
- learning agents
- multi agent systems
- e learning