TTPFTS is the first anytime algorithm for Pareto set identification in multi-objective multi-armed bandits, benchmarked on synthetic environments, applied to molecular discovery, equipped with a new uncertainty metric, and supported by an asymptotic correctness proof.
Neural Comput
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Bayesian Anytime Pareto Set Identification for Multi-Objective Multi-Armed Bandits
TTPFTS is the first anytime algorithm for Pareto set identification in multi-objective multi-armed bandits, benchmarked on synthetic environments, applied to molecular discovery, equipped with a new uncertainty metric, and supported by an asymptotic correctness proof.