Planning Using Multiple Execution Architectures
Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence. Planning. Pages 1394-1400.
Abstract
We discuss two techniques used by the RALPHMEA agent architecture to facilitate decision making in complex, real-time domains . Multiple execution architectures are four implementations of the agent function, a function that receives percepts from the environment as input and outputs an action choice. The four execution architectures arc defined by the different knowledge types that each uses. Depending on the domain and agent capabilities, each execution architecture has different speed and correctness properties. Metalevel control of planning computes the value of information of planning to compare to the utility of executing the current default plan. Examples are presented from an autonomous, underwater vehicle domain.
@inproceedings{ijcai1993p193,
title = {Planning Using Multiple Execution Architectures},
author = {Ogasawara, Gary H. and Russell, Stuart J.},
booktitle = {Proceedings of the Thirteenth International Joint Conference on
Artificial Intelligence, {IJCAI-93}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Ruzena Bajcsy},
pages = {1394--1400},
year = {1993},
note = {Planning},
url = {https://ijcai.org/proceedings/1993/193},
}
TY - CPAPER TI - Planning Using Multiple Execution Architectures AU - Ogasawara, Gary H. AU - Russell, Stuart J. T2 - Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence, IJCAI-93 PB - International Joint Conferences on Artificial Intelligence PY - 1993 SP - 1394 EP - 1400 UR - https://ijcai.org/proceedings/1993/193 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
