Online Learning and Pricing with Reusable Resources: Linear Bandits with Sub-Exponential Rewards.
Huiwen JiaCong ShiSiqian ShenPublished in: ICML (2022)
Keyphrases
- online learning
- regret bounds
- multi armed bandits
- linear complexity
- online course
- higher education
- e learning
- stochastic systems
- limited resources
- computer mediated
- reinforcement learning
- active learning
- linear systems
- resource constraints
- resource management
- software systems
- blended learning
- information resources
- distance education
- online algorithms
- distance learning
- digital libraries
- closed form
- learning environment
- online learning environments
- bandit problems
- double exponential
- machine learning