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

Multi-Armed Bandits

Benchmarks

Task NameDataset NameSOTA ResultTrend
Policy OptimizationMulti-Armed Bandits
Sample Complexity-7
8
Regret minimizationMulti-Armed Bandits (MABs) Stochastic i.i.d. setting
Metric-
0
Multi-Armed BanditsStatic Unconstrained Multi-Armed Bandits (MAB)
Metric-
0
Showing 3 of 3 rows