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

Convex arm-to-reward function

Benchmarks

Task NameDataset NameSOTA ResultTrend
Best Arm IdentificationConvex arm-to-reward function K=40 (test)
Error Rate0.25
15
Best Arm IdentificationConvex arm-to-reward function K=20 (test)
Error Probability0.21
15
Best Arm IdentificationConvex arm-to-reward function K=10 (test)
Error Rate0.62
15
Showing 3 of 3 rows