Online Action Learning in High Dimensions: A Conservative Perspective

arXiv:2009.13961v4 Announce Type: replace-cross
Abstract: Sequential learning problems are common in several fields of research and practical applications. Examples include dynamic pricing and assortment, design of auctions and incentives and permeate a large number of sequential treatment experiments. In this paper, we extend one of the most popular learning solutions, the $\epsilon_t$-greedy heuristics, to high-dimensional contexts considering a conservative directive. We do this by allocating part of the time the original rule uses to adopt completely new actions to a …

abstract applications arxiv cs.lg design dimensions dynamic dynamic pricing econ.em examples fields incentives paper perspective popular practical pricing research solutions stat.ml treatment type