dc.contributor.author |
Junyent Barbany, Miquel |
dc.contributor.author |
Gómez, Vicenç |
dc.contributor.author |
Jonsson, Anders, 1973- |
dc.date.accessioned |
2023-02-07T13:23:44Z |
dc.date.available |
2023-02-07T13:23:44Z |
dc.date.issued |
2021 |
dc.identifier.citation |
Junyent M, Gómez V, Jonsson A. Hierarchical width-based planning and learning. In: Biundo S, Do M, Goldman R, Katz M, Yang Q, Zhuo HH, editors. Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS2021); 2021 Aug 2-13; Guangzhou, China. California, United States: AAAI Press; 2021. p. 519-27. DOI: 10.1609/icaps.v31i1.15999 |
dc.identifier.issn |
2334-0835 |
dc.identifier.uri |
http://hdl.handle.net/10230/55667 |
dc.description |
Comunicació presentada a: ICAPS2021 celebrat del 2 a 13 d'agost de 2021 a Guangzhou, Xina. |
dc.description.abstract |
Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari games. These methods scale independently of the size of the state-space, but exponentially in the problem width. In practice, running the algorithm with a width larger than 1 is computationally intractable, prohibiting IW from solving higher width problems. In this paper, we present a hierarchical algorithm that plans at two levels of abstraction. A high-level planner uses abstract features that are incrementally discovered from low-level pruning decisions. We illustrate this algorithm in classical planning PDDL domains as well as in pixel-based simulator domains. In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2. For pixel-based domains, we show how in combination with a learned policy and a learned value function, the proposed hierarchical IW can outperform current flat IW-based planners in Atari games with sparse rewards. |
dc.description.sponsorship |
V. Gómez has received funding from “La Caixa” Foundation (100010434), under the agreement LCF/PR/PR16/51110009 and is supported by the Ramon y Cajal program RYC-2015-18878 (AEI/MINEICO/FSE,UE). A. Jonsson is partially supported by Spanish grants PID2019-108141GB-I00 and PCIN-2017-082. |
dc.format.mimetype |
application/pdf |
dc.language.iso |
eng |
dc.publisher |
Association for the Advancement of Artificial Intelligence (AAAI) |
dc.relation.ispartof |
Biundo S, Do M, Goldman R, Katz M, Yang Q, Zhuo HH, editors. Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS2021); 2021 Aug 2-13; Guangzhou, China. California, United States: AAAI Press; 2021. p. 519-27. |
dc.rights |
© 2021, Association for the Advancement of Artificial Intelligence (www.aaai.org) |
dc.title |
Hierarchical width-based planning and learning |
dc.type |
info:eu-repo/semantics/conferenceObject |
dc.identifier.doi |
http://dx.doi.org/10.1609/icaps.v31i1.15999 |
dc.subject.keyword |
Reinforcement Learning Using Planning (model-based, Bayesian, Deep, Etc.) |
dc.subject.keyword |
Learning To Improve The Effectiveness Of Planning & Scheduling Systems |
dc.subject.keyword |
Applications That Involve A Combination Of Learning With Planning Or Scheduling |
dc.subject.keyword |
Theoretical Aspects Of Planning And Learning |
dc.relation.projectID |
info:eu-repo/grantAgreement/ES/2PE/PID2019-108141GB-I00 |
dc.relation.projectID |
info:eu-repo/grantAgreement/ES/2PE/PCIN-2017-082 |
dc.rights.accessRights |
info:eu-repo/semantics/openAccess |
dc.type.version |
info:eu-repo/semantics/acceptedVersion |