Learning Algorithms for Markovian Bandits:\\Is Posterior Sampling more Scalable than Optimism?
Nicolas GastBruno GaujalKimang KhunPublished in: Trans. Mach. Learn. Res. (2022)
Keyphrases
- learning algorithm
- markov chain monte carlo
- machine learning algorithms
- metropolis hastings
- multi armed bandit
- active learning
- machine learning
- learning problems
- supervised learning
- probability distribution
- bayesian framework
- monte carlo
- point processes
- reinforcement learning
- back propagation
- posterior probability
- random sampling
- posterior distribution
- multi armed bandits
- learning process
- efficient learning
- probabilistic model
- learning tasks
- training samples
- learning scheme
- learning models
- stochastic systems
- class noise
- deep architectures
- transfer learning
- generative model