Multi-Task Off-Policy Learning from Bandit Feedback
This work addresses multi-task learning challenges in applications like recommender systems, offering a hierarchical approach that is incremental but provides clear gains over baseline methods.
The paper tackles the problem of learning multiple similar tasks, such as personalized recommendation policies, from logged bandit feedback by formulating it as contextual off-policy optimization in a hierarchical graphical model. The result is a proposed algorithm, HierOPO, which shows improved suboptimality bounds and empirical performance over independent task learning.
Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users with similar movie preferences, where the users may still rank the individual movies slightly differently. Such tasks can be organized in a hierarchy, where similar tasks are related through a shared structure. In this work, we formulate this problem as a contextual off-policy optimization in a hierarchical graphical model from logged bandit feedback. To solve the problem, we propose a hierarchical off-policy optimization algorithm (HierOPO), which estimates the parameters of the hierarchical model and then acts pessimistically with respect to them. We instantiate HierOPO in linear Gaussian models, for which we also provide an efficient implementation and analysis. We prove per-task bounds on the suboptimality of the learned policies, which show a clear improvement over not using the hierarchical model. We also evaluate the policies empirically. Our theoretical and empirical results show a clear advantage of using the hierarchy over solving each task independently.