Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning

Lipovetzky, Nir

doi:10.24963/ijcai.2021/702

Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning

Nir Lipovetzky

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Early Career. Pages 4956-4960.

https://doi.org/10.24963/ijcai.2021/702

Keywords

Planning and Scheduling: General
Planning and Scheduling: Theoretical Foundations of Planning
Planning and Scheduling: Planning Algorithms
Planning and Scheduling: Applications of Planning

Abstract

Width-based algorithms search for solutions through a general definition of state novelty. These algorithms have been shown to result in state-of-the-art performance in classical planning, and have been successfully applied to model-based and model-free settings where the dynamics of the problem are given through simulation engines. Width-based algorithms performance is understood theoretically through the notion of planning width, providing polynomial guarantees on their runtime and memory consumption. To facilitate synergies across research communities, this paper summarizes the area of width-based planning, and surveys current and future research directions.

Nir Lipovetzky. 2021. Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 4956–4960. https://doi.org/10.24963/ijcai.2021/702

@inproceedings{ijcai2021p702,
  title     = {Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning},
  author    = {Lipovetzky, Nir},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {4956--4960},
  year      = {2021},
  month     = {8},
  note      = {Early Career},
  doi       = {10.24963/ijcai.2021/702},
  url       = {https://doi.org/10.24963/ijcai.2021/702},
}

TY  - CPAPER
TI  - Width-Based Algorithms for Common Problems in Control, Planning and Reinforcement Learning
AU  - Lipovetzky, Nir
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 4956
EP  - 4960
DO  - 10.24963/ijcai.2021/702
UR  - https://doi.org/10.24963/ijcai.2021/702
ER  -