Home > Research > Publications & Outputs > Information-guided Planning

Electronic data

  • Main paper - Author version

    Accepted author manuscript, 1.82 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

View graph of relations

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Forthcoming
Publication date21/09/2023
Host publicationThirty-seventh Conference on Neural Information Processing Systems
<mark>Original language</mark>English
EventThirty-seventh Conference on Neural Information Processing Systems: 37th Anniversary Conference - Ernest N. Morial Convention Center, New Orleans, United States
Duration: 10/12/202316/12/2023
Conference number: 37
https://neurips.cc/

Conference

ConferenceThirty-seventh Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2023
Country/TerritoryUnited States
CityNew Orleans
Period10/12/2316/12/23
Internet address

Conference

ConferenceThirty-seventh Conference on Neural Information Processing Systems
Abbreviated titleNeurIPS 2023
Country/TerritoryUnited States
CityNew Orleans
Period10/12/2316/12/23
Internet address

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.