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

Linear arm-to-reward function

Benchmarks

Task NameDataset NameSOTA ResultTrend
Best Arm IdentificationLinear arm-to-reward function K=40
Error Rate10.67
15
Best Arm IdentificationLinear arm-to-reward function K=20
Error Probability3.73
15
Best Arm IdentificationLinear arm-to-reward function K=10
Error Probability0.0055
15
Showing 3 of 3 rows