A Discussion on the Scalability of Heuristic Approximators (Extended Abstract) Academic Article uri icon

abstract

  • In this work, we examine a line of recent publications that propose to use deep neural networks to approximate the goal distances of states for heuristic search. We present a first step toward showing that this work suffers from inherent scalability limitations since --- under the assumption that PNP --- such approaches require network sizes that scale exponentially in the number of states to achieve the necessary (high) approximation accuracy.

published proceedings

  • Proceedings of the International Symposium on Combinatorial Search

author list (cited authors)

  • Pendurkar, S., Huang, T., Koenig, S., & Sharon, G.

citation count

  • 0

complete list of authors

  • Pendurkar, Sumedh||Huang, Taoan||Koenig, Sven||Sharon, Guni

publication date

  • January 2022