Sequential learning of the Pareto front for multi-objective bandits.
Élise CreponAurélien GarivierWouter M. KoolenPublished in: AISTATS (2024)
Keyphrases
- multi objective
- multi objective optimization
- learning algorithm
- learning tasks
- optimization algorithm
- learning process
- active learning
- learning systems
- evolutionary algorithm
- multi objective optimization problems
- pareto optimal
- learning problems
- background knowledge
- reinforcement learning
- mobile learning
- unsupervised learning
- particle swarm optimization
- knowledge acquisition
- learning community
- multiple objectives
- prior knowledge