Adversarial Bandits against Arbitrary Strategies

Abstract
We study the adversarial bandit problem against arbitrary strategies, in which is the parameter for the hardness of the problem and this parameter is not given to the agent. To handle this problem, we adopt the master-base framework using the online mirror descent method (OMD). We first provide a master-base algorithm with simple OMD, achieving , in which comes from the variance of loss estimators. To mitigate the impact of the variance, we propose using adaptive learning rates for OMD and achieve , where is a variance term for loss estimators.
View on arXivComments on this paper