Factor Selection for Reinforcement Learning in HTTP Adaptive Streaming.
Tingyao WuWerner Van LeekwijckPublished in: MMM (1) (2014)
Keyphrases
- reinforcement learning
- function approximation
- website
- optimal policy
- scalable video
- open source
- adaptive control
- state space
- supervised learning
- real time
- learning algorithm
- selection algorithm
- video streaming
- learning capabilities
- computational complexity
- markov decision processes
- selection strategy
- selection criteria
- data sets