Probabilistic Planning with Sequential Monte Carlo Methods
Abstract
In this work, we propose a novel formulation of planning which views it as a probabilistic inference problem over future optimal trajectories. This enables us to use sampling methods, and thus, tackle planning in continuous domains using a fixed computational budget. We design a new algorithm, Sequential Monte Carlo Planning, by leveraging classical methods in Sequential Monte Carlo and Bayesian smoothing in the context of control as inference. Furthermore, we show that Sequential Monte Carlo Planning can capture multimodal policies and can quickly learn continuous control tasks.
Cite
Text
Piche et al. "Probabilistic Planning with Sequential Monte Carlo Methods." International Conference on Learning Representations, 2019.Markdown
[Piche et al. "Probabilistic Planning with Sequential Monte Carlo Methods." International Conference on Learning Representations, 2019.](https://mlanthology.org/iclr/2019/piche2019iclr-probabilistic/)BibTeX
@inproceedings{piche2019iclr-probabilistic,
title = {{Probabilistic Planning with Sequential Monte Carlo Methods}},
author = {Piche, Alexandre and Thomas, Valentin and Ibrahim, Cyril and Bengio, Yoshua and Pal, Chris},
booktitle = {International Conference on Learning Representations},
year = {2019},
url = {https://mlanthology.org/iclr/2019/piche2019iclr-probabilistic/}
}