Causal Bandits: The Pareto Optimal Frontier of Adaptivity, a Reduction to Linear Bandits, and Limitations around Unknown Marginals.
Ziyi LiuIdan AttiasDaniel M. RoyPublished in: CoRR (2024)
Keyphrases
- pareto optimal
- multi objective
- regret bounds
- multi objective optimization
- stochastic systems
- pareto optimality
- nash equilibrium
- multi issue negotiation
- multiple objectives
- nsga ii
- pareto optimal set
- probability distribution
- message passing
- graphical models
- evolutionary algorithm
- optimal solution
- particle swarm optimization
- joint distribution
- np hard
- lower bound