Identifying internal parameters for planning is crucial to maximizing the performance of a planner. However, automatically tuning internal parameters which are conditioned on the problem instance is especially challenging. A recent line of work focuses on learning planning parameter generators, but lack a consistent problem definition and software framework. This work proposes the unified planner optimization problem (POP) formulation, along with the Open Planner Optimization Framework (OPOF), a highly extensible software framework to specify and to solve these problems in a reusable manner.
@article{arxiv.2303.06768,
title = {The Planner Optimization Problem: Formulations and Frameworks},
author = {Yiyuan Lee and Katie Lee and Panpan Cai and David Hsu and Lydia E. Kavraki},
journal= {arXiv preprint arXiv:2303.06768},
year = {2023}
}