On the Sublinear Regret of GP-UCB.
Justin WhitehouseAaditya RamdasZhiwei Steven WuPublished in: NeurIPS (2023)
Keyphrases
- bandit problems
- genetic programming
- multi armed bandit
- multi armed bandit problems
- decision problems
- fitness function
- online learning
- reinforcement learning
- lower bound
- confidence bounds
- upper confidence bound
- regret bounds
- expert advice
- evolutionary algorithm
- upper bound
- loss function
- worst case
- cost sensitive
- binary classification
- expected utility
- gradient projection
- genetic algorithm