do Carmo Alves, M. A., Varma, A., Elkhatib, Y. and Marcolino, L. S. (2023) Information-Guided Planning: An Online Approach for Partially Observable Problems. In: NeurIPS 2023, New Orleans, USA, 10-16 December 2023,
Text
308909.pdf - Accepted Version 2MB |
Publisher's URL: https://proceedings.neurips.cc/paper_files/paper/2023/hash/da5498f88193ff61f0daea1940b819da-Abstract-Conference.html
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.
Item Type: | Conference Proceedings |
---|---|
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Elkhatib, Dr Yehia |
Authors: | do Carmo Alves, M. A., Varma, A., Elkhatib, Y., and Marcolino, L. S. |
College/School: | College of Science and Engineering > School of Computing Science |
Copyright Holders: | Copyright © The Author(s) 2023 |
First Published: | First published in Advances in Neural Information Processing Systems 36 (NeurIPS 2023) |
Publisher Policy: | Reproduced with the permission of the publisher |
Related URLs: |
University Staff: Request a correction | Enlighten Editors: Update this record