Lifelong bandit optimization: no prior and no regret.
Felix SchurParnian KassraieJonas RothfussAndreas KrausePublished in: UAI (2023)
Keyphrases
- bandit problems
- optimization algorithm
- online learning
- global optimization
- upper confidence bound
- optimization problems
- regret bounds
- optimization method
- learning scenarios
- optimization model
- multi armed bandit problems
- genetic algorithm
- multi armed bandit
- expert advice
- technology enhanced learning
- constrained optimization
- optimization methods
- decision problems
- worst case
- prior knowledge
- lower bound