Reinforcement Learning for Proactive Caching of Contents with Different Demand Probabilities.
Samuel O. SomuyiwaDeniz GündüzAndrás GyörgyPublished in: ISWCS (2018)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- multi agent
- robotic control
- model free
- markov decision processes
- probability distribution
- temporal difference
- multimedia
- data access
- machine learning
- access patterns
- prefetching
- caching scheme
- probability theory
- dynamic content
- lead time
- learning process
- web content
- query processing
- context aware
- transition model
- hit ratio
- belief networks
- action selection
- optimal control
- learning problems
- response time
- metadata