List your company

Stochastic Multi-Armed Bandit on K-armed Gaussian bandit Model 1

337.7RegretUCB1
308.356506.428704.5902.572Feb 12, 2024

Evaluation results

MethodLinks
UCB1Number of time steps T=10,000, Confidence bounds=two-sigma2024.02337.7
RECNumber of time steps T=10,000, Confidence bounds=two-sigma2024.02597.2
RSENumber of time steps T=10,000, Confidence bounds=two-sigma2024.02625.8
RASMABNumber of time steps T=10,000, Confidence bounds=two-sigma2024.021,071.3