Corruption-tolerant bandit learning
Sign Up to like & getrecommendations! Published in 2018 at "Machine Learning"
DOI: 10.1007/s10994-018-5758-5
Abstract: We present algorithms for solving multi-armed and linear-contextual bandit tasks in the face of adversarial corruptions in the arm responses. Traditional algorithms for solving these problems assume that nothing but mild, e.g., i.i.d. sub-Gaussian, noise… read more here.
Keywords: learning corruption; corruption tolerant; algorithms; bandit ... See more keywords