Multi-Agent Systems by Incremental Gradient Reinforcement Learning
Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence. Pages 833-837.
Abstract
A new reinforcement learning (RL) methodology is proposed to design multi-agent systems. In the realistic setting of situated agents with local perception, the task of automatically building a coordinated system is of crucial importance. We use simple reactive agents which learn their own behavior in a decentralized way. To cope with the difficulties inherent to RL used in that framework, we have developed an incremental learning algorithm where agents face more and more complex tasks. We illustrate this general framework on a computer experiment where agents have to coordinate to reach a global goal.
@inproceedings{ijcai2001p114,
title = {Multi-Agent Systems by Incremental Gradient Reinforcement Learning},
author = {Dutech, Alain and Buffet, Olivier and Charpillet, François},
booktitle = {Proceedings of the Seventeenth International Joint Conference on
Artificial Intelligence, {IJCAI-01}},
publisher = {International Joint Conferences on Artificial Intelligence},
pages = {833--837},
year = {2001},
url = {https://ijcai.org/proceedings/2001/114},
}
TY - CPAPER TI - Multi-Agent Systems by Incremental Gradient Reinforcement Learning AU - Dutech, Alain AU - Buffet, Olivier AU - Charpillet, François T2 - Proceedings of the Seventeenth International Joint Conference on Artificial Intelligence, IJCAI-01 PB - International Joint Conferences on Artificial Intelligence PY - 2001 SP - 833 EP - 837 UR - https://ijcai.org/proceedings/2001/114 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
