Coordination and Multi-Tasking Using EMT
Abstract
We introduce a multi-model variant of the EMT-based con-trol algorithm. The new algorithm, MM-EMT, is capable of balancing several control tasks expressed using separate dy-namic models with a common action space. Such multiple models are common in both single-agent environments, when the agent has multiple tasks to achieve, and in team activities, when agent actions affect both the local agent’s task as well as the overall team’s coordination. To demonstrate the behaviour that MM-EMT engenders, sev-eral experimental setups were devised. Simulation results support the effectiveness of the approach, which in the multi-agent scenario is expressed in the MM-EMT algorithm’s abil-ity to balance local and team-coordinated motion require-ments.
Cite
Text
Rabinovich et al. "Coordination and Multi-Tasking Using EMT." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Rabinovich et al. "Coordination and Multi-Tasking Using EMT." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/rabinovich2008aaai-coordination/)BibTeX
@inproceedings{rabinovich2008aaai-coordination,
title = {{Coordination and Multi-Tasking Using EMT}},
author = {Rabinovich, Zinovi and Pochter, Nir and Rosenschein, Jeffrey S.},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {144-149},
url = {https://mlanthology.org/aaai/2008/rabinovich2008aaai-coordination/}
}