Monte-Carlo Tree Search and Reinforcement Learning for Reconfiguring Data Stream Processing on Edge Computing.
Alexandre da Silva VeithMarcos Dias de AssunçãoLaurent LefèvrePublished in: SBAC-PAD (2019)
Keyphrases
- monte carlo tree search
- reinforcement learning
- reinforcement learning methods
- temporal difference
- bayesian reinforcement learning
- data stream processing
- temporal difference learning
- monte carlo
- evaluation function
- data flow
- stream processing
- function approximation
- reinforcement learning algorithms
- learning agent
- state space
- data streams
- learning algorithm
- markov decision processes
- machine learning
- action selection
- supervised learning
- function approximators
- training set
- data analysis