Sequential Transfer in Multi-armed Bandit with Finite Set of Models

Emma Brunskill - Carnegie Mellon University

March 21, 2014, 1 p.m. - March 21, 2014, 2 p.m.


Learning from prior tasks and transferring that experience to improve future performance is critical for building lifelong learning agents. Although results in supervised and reinforcement learning show that transfer may significantly improve the learning performance, most of the literature on transfer is focused on batch learning tasks. In this paper we study the problem of sequential transfer in online learning, notably in the multi-armed bandit framework, where the objective is to minimize the total regret over a sequence of tasks by transferring knowledge from prior tasks. We introduce a novel bandit algorithm based on a method-of-moments approach for estimating the possible tasks and derive regret bounds for it. Emma Brunskill is an assistant professor in the computer science department at Carnegie Mellon University. She is also affiliated with the machine learning department at CMU. She works on interactive machine learning, focusing on applications that involve artificial agents interacting with people, such as intelligent tutoring systems. For her research Emma was selected as a Microsoft Faculty Fellow.