Unifying the stochastic and the adversarial Bandits with Knapsack.
Anshuka RangiMassimo FranceschettiLong Tran-ThanhPublished in: CoRR (2018)
Keyphrases
- stochastic systems
- dynamic programming
- knapsack problem
- monte carlo
- learning automata
- data sets
- regret bounds
- stochastic optimization
- multi armed bandits
- stochastic models
- multiple choice
- artificial intelligence
- confidence intervals
- expert systems
- markov processes
- multiscale
- machine learning
- multi armed bandit
- real time