Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Multi-armed Bandit

Benchmarks

Task NameDataset NameSOTA ResultTrend
Regret MinimizationMulti-armed Bandit anytime setting
Regret Coefficient2
5
Regret MinimizationAdversarial Multi-Armed Bandit (MAB)
Regret2
1
Showing 2 of 2 rows