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

Wheel Bandit

Benchmarks

Task NameDataset NameSOTA ResultTrend
Contextual BanditWheel Bandit delta=0.99
Normalized Cumulative Regret86.03
9
Contextual BanditWheel Bandit delta=0.95
Normalized Cumulative Regret63.3
9
Contextual BanditWheel Bandit delta=0.90
Normalized Cumulative Regret36.54
9
Contextual BanditWheel Bandit (delta=0.70)
Normalized Cumulative Regret13.72
9
Contextual BanditWheel Bandit delta=0.50
Normalized Cumulative Regret12.49
9
Showing 5 of 5 rows