Raising Expectations in GDA Agents Acting in Dynamic Environments
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2241-2246.
Abstract
Goal-driven autonomy (GDA) agents reason about goals while introspectively examining if their course of action matches their expectations. Many GDA agents adopt a hierarchical planning model to generate plans but limit reasoning with expectations to individual actions or projecting the expected state. In this paper we present a relaxation of this limitation. Taking advantage of hierarchical planning principles, our GDA agent elicits expectations that not only validate the next action but the overall plan trajectory without requiring validation against the complete state. We report on (1) a formalization of GDA's expectations that covers trajectories, (2) an implementation of these ideas and (3) benchmarking on two domains used in the GDA literature.
@inproceedings{ijcai2015p317,
title = {Raising Expectations in GDA Agents Acting in Dynamic Environments},
author = {Dannenhauer, Dustin and Muñoz-Avila, Héctor},
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 = {2241--2246},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/317},
}
TY - CPAPER TI - Raising Expectations in GDA Agents Acting in Dynamic Environments AU - Dannenhauer, Dustin AU - Muñoz-Avila, Héctor T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 2241 EP - 2246 UR - https://ijcai.org/proceedings/2015/317 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
