Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model.
Cheng ChenCanzhe ZhaoShuai LiPublished in: CoRR (2022)
Keyphrases
- prior knowledge
- computational model
- conceptual model
- high level
- mathematical model
- learning algorithm
- learning process
- learning mechanism
- learning scheme
- learning models
- monte carlo
- reinforcement learning
- management system
- active learning
- objective function
- learning systems
- unsupervised learning
- bayesian networks
- maximum likelihood
- hidden variables
- multi agent
- stochastic model
- stochastic process
- stochastic programming
- boltzmann machine
- stochastic nature