List your company

Bandit Regret Minimization on Wheel Bandit delta=0.95

8,211.9Mean Cumulative RegretGradient-Laplace
6,652.9817,175.6927,698.438,221.11May 9, 2026

Evaluation results

MethodLinks
Gradient-Laplacek=5002026.058,211.9355
Greedy-Laplacek=5002026.058,616.7574.5
Greedy-Laplacek=1002026.0521,568.75,895.4
NeuralLineark=N/A2026.0530,2666,572.7
Last kk=5002026.0530,556.27,942.9
Subnet Diagonalk=5002026.0533,796.47,464.6
Last kk=1002026.0535,340.17,576.7
Gradient-Laplacek=1002026.0538,177.46,904.8
MAP (no exploration)k=N/A2026.0543,298.97,146.9
Subnet Diagonalk=1002026.0547,184.97,275.3