Reinforcement learning (RL) is a subfield of machine learning dedicated to teaching agents to make a sequence of decisions through interactions with a dynamic environment. In RL, an agent observes ...

Although originally designed for prediction problems, it is natural to inquire about their suitability in another important field, sequential decision-making and reinforcement learning problems ...

We then introduce approaches for integrating model-based planning with learning-based components via compositional learning. Lastly, we propose a novel application area of sequential decision making ...