Model-Assisted Deep Reinforcement Learning for Dynamic Wireless Scheduling.
Arjun AnandRavikumar BalakrishnanV. Srinivasa SomayazuluRath VannithambyPublished in: ACSSC (2020)
Keyphrases
- high level
- data sets
- theoretical analysis
- probabilistic model
- reinforcement learning
- prior knowledge
- neural network
- mathematical model
- computational model
- management system
- objective function
- experimental data
- similarity measure
- probability distribution
- information systems
- genetic algorithm
- multi layer
- dynamically updated
- resource allocation
- dynamic programming
- image segmentation
- learning algorithm