Learning first-order representations for planning from black box states: new results
Mostra el registre complet Registre parcial de l'ítem
- dc.contributor.author Rodriguez, Ivan D.
- dc.contributor.author Bonet, Blai
- dc.contributor.author Romero, Javier
- dc.contributor.author Geffner, Héctor
- dc.date.accessioned 2023-02-09T13:11:56Z
- dc.date.available 2023-02-09T13:11:56Z
- dc.date.issued 2021
- dc.description Comunicació presentada a 18th International Conference on Principles of Knowledge Representation and Reasoning (KR2021), celebrat del 3 al 12 de novembre de 2021 de manera virtual.
- dc.description.abstract Recently Bonet and Geffner have shown that first-order representations for planning domains can be learned from the structure of the state space without any prior knowledge about the action schemas or domain predicates. For this, the learning problem is formulated as the search for a simplest first-order domain description D that along with information about instances I_i (number of objects and initial state) determine state space graphs G(P_i) that match the observed state graphs G_i where P_i = (D, I_i). The search is cast and solved approximately by means of a SAT solver that is called over a large family of propositional theories that differ just in the parameters encoding the possible number of action schemas and domain predicates, their arities, and the number of objects. In this work, we push the limits of these learners by moving to an answer set programming (ASP) encoding using the CLINGO system. The new encodings are more transparent and concise, extending the range of possible models while facilitating their exploration. We show that the domains introduced by Bonet and Geffner can be solved more efficiently in the new approach, often optimally, and furthermore, that the approach can be easily extended to handle partial information about the state graphs as well as noise that prevents some states from being distinguished.
- dc.description.sponsorship The work is partially supported by an ERC Advanced Grant (No 885107), by project TAILOR, funded by an EU Horizon 2020 Grant (No 952215), and by the Knut and Alice Wallenberg (KAW) Foundation under the WASP program.
- dc.format.mimetype application/pdf
- dc.identifier.citation Rodriguez ID, Bonet B, Romero J, Geffner H. Learning first-order representations for planning from black box states: new results. In: Bienvenu M, Lakemeyer G, Erdem E, editors. Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning; 2021 Nov 3-12; online. [Montreal]: IJCAI Organization; 2021. p. 539-48. DOI: 10.24963/kr.2021/51
- dc.identifier.doi http://dx.doi.org/10.24963/kr.2021/51
- dc.identifier.issn 2334-1033
- dc.identifier.uri http://hdl.handle.net/10230/55704
- dc.language.iso eng
- dc.publisher International Joint Conferences on Artificial Intelligence Organization
- dc.relation.ispartof Bienvenu M, Lakemeyer G, Erdem E, editors. Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning; 2021 Nov 3-12; online. [Montreal]: IJCAI Organization; 2021. p. 539-48.
- dc.relation.isreferencedby https://github.com/bonetblai/learner-strips/tree/master/asp
- dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/952215
- dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/885107
- dc.rights © 2021 International Joint Conferences on Artificial Intelligence. This is the published version of a paper available at https://doi.org/10.24963/kr.2021/51 that appeared in the Proceedings of the 18th International Conference on Principles of Knowledge Representation and Reasoning.
- dc.rights.accessRights info:eu-repo/semantics/openAccess
- dc.subject.keyword Learning action theories
- dc.subject.keyword Learning symbolic abstractions from unstructured data
- dc.title Learning first-order representations for planning from black box states: new results
- dc.type info:eu-repo/semantics/conferenceObject
- dc.type.version info:eu-repo/semantics/publishedVersion