List your company

Multi-armed Bandit Regret Minimization on K-armed bandits

1Minimax RatioMOTS
0.950.97511.025Jun 7, 2022

Evaluation results

MethodLinks
MOTSReward Type=sub-Gaussian, Anytime=false2022.061——
MOTS-JReward Type=Gaussian, Anytime=false2022.061——
ExpTS+Reward Type=Exponential Family, Anytime=true2022.061——