Information-Guided Planning: An Online Approach for Partially Observable Problems

Abstract

This paper presents IB-POMCP, a novel algorithm for online planning under partial observability. Our approach enhances the decision-making process by using estimations of the world belief's entropy to guide a tree search process and surpass the limitations of planning in scenarios with sparse reward configurations. By performing what we denominate as an information-guided planning process, the algorithm, which incorporates a novel I-UCB function, shows significant improvements in reward and reasoning time compared to state-of-the-art baselines in several benchmark scenarios, along with theoretical convergence guarantees.

Cite

Text

Alves et al. "Information-Guided Planning: An Online Approach for Partially Observable Problems." Neural Information Processing Systems, 2023.

Markdown

[Alves et al. "Information-Guided Planning: An Online Approach for Partially Observable Problems." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/alves2023neurips-informationguided/)

BibTeX

@inproceedings{alves2023neurips-informationguided,
  title     = {{Information-Guided Planning: An Online Approach for Partially Observable Problems}},
  author    = {Alves, Matheus Aparecido Do Carmo and Varma, Amokh and Elkhatib, Yehia and Marcolino, Leandro Soriano},
  booktitle = {Neural Information Processing Systems},
  year      = {2023},
  url       = {https://mlanthology.org/neurips/2023/alves2023neurips-informationguided/}
}