Managing caching strategies for stream reasoning with reinforcement learning.
Carmine DodaroThomas EiterPaul OgrisKonstantin SchekotihinPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- caching strategies
- response time
- web search engines
- data streams
- reasoning systems
- machine learning
- function approximation
- sliding window
- reasoning process
- state space
- model based reasoning
- knowledge base
- markov decision processes
- spatial reasoning
- neural network
- reasoning mechanisms
- analogical reasoning
- learning algorithm
- model free
- learning problems
- real time
- artificial intelligence
- multi agent
- action selection
- temporal difference
- automated reasoning
- information retrieval
- web documents
- temporal difference learning
- bayesian networks
- transition model
- domain knowledge