Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners.
Mohammadi ZakiAvinash MohanAditya GopalanPublished in: CoRR (2020)
Keyphrases
- multi armed bandit problems
- regret bounds
- e learning
- bandit problems
- learning environment
- online learning
- learning activities
- lower bound
- learning materials
- learning strategies
- multi armed bandit
- learning process
- learning experience
- collaborative learning
- multi armed bandits
- learning systems
- learning resources
- learning community
- linear model
- concept mapping
- concept maps
- teaching materials
- linear systems
- social learning
- robotic arm
- upper bound
- convex optimization