Predicting Contextual Sequences via Submodular Function Maximization
This work addresses sequence optimization for applications like web advertising and robotics, offering a contextual approach that is incremental over previous static methods.
The paper tackles the problem of ordering items in a sequence based on context, such as perceptual information or goals, by proposing a reduction-based approach that uses submodular function maximization to convert sequence optimization into cost-sensitive prediction. It demonstrates results on robotics tasks like manipulator trajectory prediction and mobile robot path planning.
Sequence optimization, where the items in a list are ordered to maximize some reward has many applications such as web advertisement placement, search, and control libraries in robotics. Previous work in sequence optimization produces a static ordering that does not take any features of the item or context of the problem into account. In this work, we propose a general approach to order the items within the sequence based on the context (e.g., perceptual information, environment description, and goals). We take a simple, efficient, reduction-based approach where the choice and order of the items is established by repeatedly learning simple classifiers or regressors for each "slot" in the sequence. Our approach leverages recent work on submodular function maximization to provide a formal regret reduction from submodular sequence optimization to simple cost-sensitive prediction. We apply our contextual sequence prediction algorithm to optimize control libraries and demonstrate results on two robotics problems: manipulator trajectory prediction and mobile robot path planning.