Behavior Networks for Continuous Domains using Situation-Dependent Motivations
Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence. Software Agents. Pages 1233-1237.
Abstract
The problem of action selection by autonomous agents becomes increasingly difficult when acting in continuous, non-deterministic and dynamic environments pursuing multiple and possibly conflicting goals. We propose a method that exploits additional information gained from continuous states, is able to deal with unexpected situations, and takes multiple and conflicting goals into account including additional motivational aspects such as dynamic goals, which allow for situation-dependent motivational influence on the agent. Further we show some domain independent properties of this algorithm along with empirical results gained using the RoboCup simulated soccer environment.
@inproceedings{ijcai1999p175,
title = {Behavior Networks for Continuous Domains using Situation-Dependent Motivations},
author = {Dorer, Klaus},
booktitle = {Proceedings of the Sixteenth International Joint Conference on
Artificial Intelligence, {IJCAI-99}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Thomas Dean},
pages = {1233--1237},
year = {1999},
note = {Software Agents},
url = {https://ijcai.org/proceedings/1999/175},
}
TY - CPAPER TI - Behavior Networks for Continuous Domains using Situation-Dependent Motivations AU - Dorer, Klaus T2 - Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence, IJCAI-99 PB - International Joint Conferences on Artificial Intelligence PY - 1999 SP - 1233 EP - 1237 UR - https://ijcai.org/proceedings/1999/175 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
