A neural network for decision making in real-time heuristic search

Franco Munoz, Miguel Fadic, Carlos Hernandez, Jorge A. Baier

Resultado de la investigación: Contribución a los tipos de informe/libroContribución a la conferenciarevisión exhaustiva

1 Cita (Scopus)

Resumen

Most real-time heuristic search algorithms solve search problems by executing a series of episodes. During each episode the algorithm decides an action for execution. Such a decision is usually made using information gathered by running a bounded, heuristic-search algorithm. In this paper we report on a real-time search algorithm that does not use a search algorithm to choose the next action to be applied. Rather, it uses a neural network whose input is local information about the search graph, comparable to the information that would be used by a bounded search algorithm. We describe a supervised learning approach to training such a network. Our three types of maps from the Moving AI benchmarks, shows that our algorithm is, in some cases, substantially superior to algorithms that have access to the same information about the graph. One of our most important conclusions is that our extended set of features important: indeed, using features beyond the heuristic seems key to achieving good performance.

Idioma originalInglés
Título de la publicación alojadaProceedings of the 11th International Symposium on Combinatorial Search, SoCS 2018
EditoresVadim Bulitko, Sabine Storandt
EditorialAAAI press
Páginas173-177
Número de páginas5
ISBN (versión digital)9781577358022
EstadoPublicada - 2018
Evento11th International Symposium on Combinatorial Search, SoCS 2018 - Stockholm, Suecia
Duración: 14 jul 201815 jul 2018

Serie de la publicación

NombreProceedings of the 11th International Symposium on Combinatorial Search, SoCS 2018

Conferencia

Conferencia11th International Symposium on Combinatorial Search, SoCS 2018
País/TerritorioSuecia
CiudadStockholm
Período14/07/1815/07/18

Áreas temáticas de ASJC Scopus

  • Redes de ordenadores y comunicaciones

Huella

Profundice en los temas de investigación de 'A neural network for decision making in real-time heuristic search'. En conjunto forman una huella única.

Citar esto