Towards an Understanding of Decision-Time vs. Background Planning in Model-Based Reinforcement Learning
Abstract: In model-based reinforcement learning, an agent can leverage a learned model to improve its way of behaving in different ways. Two of the prevalent approaches are decision-time planning and background planning. In this study, we are interested in understanding under what conditions and in which settings one of these two planning styles will perform better than the other. After viewing them in a unified way through the lens of dynamic programming, we first consider the simplest instantiations of these planning styles and provide theoretical results and hypotheses on which one will perform better in the planning & learning and transfer learning settings. We then consider the modern instantiations of them and provide hypotheses on which one will perform better in the considered settings. Lastly, we perform several experiments to illustrate and validate both our theoretical results and hypotheses. Overall, our findings suggest that even though decision-time planning does not perform as well as background planning in its simplest instantiations, the modern instantiations of it can perform on par or better than the modern instantiations of background planning in both the planning & learning and transfer learning settings.
Submission Length: Long submission (more than 12 pages of main content)
Assigned Action Editor: ~Mirco_Mutti1
Submission Number: 1565
Loading