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

Bandit Regret Minimization on Wheel Bandit delta=0.95

8,211.9Mean Cumulative Regret

Gradient-Laplace

6,652.9817,175.6927,698.438,221.11May 9, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
8,211.9355
2026.05
8,616.7574.5
2026.05
21,568.75,895.4
2026.05
30,2666,572.7
2026.05
30,556.27,942.9
2026.05
33,796.47,464.6
2026.05
35,340.17,576.7
2026.05
38,177.46,904.8
43,298.97,146.9
2026.05
47,184.97,275.3