Pareto Regret Analyses in Multi-objective Multi-armed Bandit.
Mengfan XuDiego KlabjanPublished in: ICML (2023)
Keyphrases
- multi objective
- multi armed bandit
- multi objective optimization
- multi armed bandits
- evolutionary algorithm
- regret bounds
- optimization algorithm
- multiobjective optimization
- reinforcement learning
- genetic algorithm
- multiple objectives
- pareto optimal
- objective function
- nsga ii
- decentralized decision making
- bandit problems
- online learning