We consider the problem of learning heuristics for numeric planning domains, using Graph Neural Networks. The problem has been approached multiple times, from different perspectives and with varying results for classical planning, but is relatively new for numeric planning. The goal is to extend the work proposed by St ̇𝑎lberg, Bonet, and Geffner [1] to handle numeric planning problems.
Learning Heuristics with Graph Neural Networks for Numeric Planning: A Preliminary Study / Borelli, Valerio; Gerevini, Alfonso Emilio; Scala, Enrico; Serina, Ivan. - 3914:(2024). ( 2024 Conference of the Italian Association for Artificial Intelligence (AIxIA) Doctoral Consortium, AIxIA-DC 2024 Bolzano, Italia ).
Learning Heuristics with Graph Neural Networks for Numeric Planning: A Preliminary Study
Borelli, Valerio
Primo
;Gerevini, Alfonso Emilio;Scala, Enrico;Serina, Ivan
2024
Abstract
We consider the problem of learning heuristics for numeric planning domains, using Graph Neural Networks. The problem has been approached multiple times, from different perspectives and with varying results for classical planning, but is relatively new for numeric planning. The goal is to extend the work proposed by St ̇𝑎lberg, Bonet, and Geffner [1] to handle numeric planning problems.| File | Dimensione | Formato | |
|---|---|---|---|
|
Borelli_Learning-Heuristics_2024.pdf
accesso aperto
Note: https://ceur-ws.org/Vol-3914/short76.pdf
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Creative commons
Dimensione
275.29 kB
Formato
Adobe PDF
|
275.29 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
