Meta-Learning for Planning: Automatic Synthesis of Sample Based Planners
Abstract
In this paper, we discuss the challenge of generating domain-specific path planners in a data-driven fashion. Via the multi-objective optimization of Python code, we synthesize new sampling-based path planners that allow robots to adapt to new tasks and environments involving sequential decision-making. In addition to the ability to adapt to new environments, our approach also enables robots to balance their computational needs with improvements in task performance. We show that new computer programs can be generated which represent diverse variants of RRT* optimized to StarCraft maps.
Cite
Text
Saldyt and Amor. "Meta-Learning for Planning: Automatic Synthesis of Sample Based Planners." ICLR 2021 Workshops: Learning_to_Learn, 2021.Markdown
[Saldyt and Amor. "Meta-Learning for Planning: Automatic Synthesis of Sample Based Planners." ICLR 2021 Workshops: Learning_to_Learn, 2021.](https://mlanthology.org/iclrw/2021/saldyt2021iclrw-metalearning/)BibTeX
@inproceedings{saldyt2021iclrw-metalearning,
title = {{Meta-Learning for Planning: Automatic Synthesis of Sample Based Planners}},
author = {Saldyt, Lucas Paul and Amor, Heni},
booktitle = {ICLR 2021 Workshops: Learning_to_Learn},
year = {2021},
url = {https://mlanthology.org/iclrw/2021/saldyt2021iclrw-metalearning/}
}