This is the PyTorch code for the following paper, in which we proposed a deep model for POMDPs planning.
Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs, by Yunbo Wang, Bo Liu, Jiajun Wu, Yuke Zhu, Simon S. Du, Li Fei-Fei and Joshua B. Tenenbaum.
We currently release the code for the first experimental domain, the floor positioning. The rest of the code for the 3D light-dark navigation domain and the modified Reacher domain will be released later. All experiments are reproducible.
Please remember to cite our paper if you use the code.
@article{wang2019dual,
title={Dual Sequential Monte Carlo: Tunneling Filtering and Planning in Continuous POMDPs},
author={Wang, Yunbo and Liu, Bo and Wu, Jiajun and Zhu, Yuke and Du, Simon S and Fei-Fei, Li and Tenenbaum, Joshua B},
journal={arXiv preprint arXiv:1909.13003},
year={2019}
}