Contextual Bandits with Stochastic Experts.
Rajat SenKarthikeyan ShanmugamSanjay ShakkottaiPublished in: CoRR (2018)
Keyphrases
- stochastic systems
- contextual information
- stochastic models
- regret bounds
- stochastic nature
- stochastic optimization
- context sensitive
- monte carlo
- multi armed bandit
- data sets
- expert advice
- probability distribution
- bayesian networks
- dynamic programming
- markov processes
- artificial intelligence
- information retrieval
- machine learning
- neural network
- databases