Sorting Sequential Portfolios in Automated Planning
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1638-1643.
Abstract
Recent work in portfolios of problem solvers has shown their ability to outperform single-algorithm approaches in some tasks (e.g. SAT or Automated Planning). However, not much work has been devoted to a better understanding of the relationship between the order of the component solvers and the performance of the resulting portfolio over time. We propose to sort the component solvers in a sequential portfolio, such that the resulting ordered portfolio maximizes the probability of providing the largest performance at any point in time. We empirically show that our greedy approach efficiently obtains near-optimal performance over time. Also, it generalizes much better than an optimal approach which has been observed to suffer from overfitting.
@inproceedings{ijcai2015p234,
title = {Sorting Sequential Portfolios in Automated Planning},
author = {Núñez, Sergio and Borrajo, Daniel and Linares López, Carlos},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {1638--1643},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/234},
}
TY - CPAPER TI - Sorting Sequential Portfolios in Automated Planning AU - Núñez, Sergio AU - Borrajo, Daniel AU - Linares López, Carlos T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 1638 EP - 1643 UR - https://ijcai.org/proceedings/2015/234 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
