AAAI 2024technical0 citations
Multi-Expert Distillation for Few-Shot Coordination (Student Abstract)
Yujian Zhu, Hao Ding, Zongzhang Zhang
Abstract
Ad hoc teamwork is a crucial challenge that aims to design an agent capable of effective collaboration with teammates employing diverse strategies without prior coordination. However, current Population-Based Training (PBT) approaches train the ad hoc agent through interaction with diverse teammates from scratch, which suffer from low efficiency. We introduce Multi-Expert Distillation (MED), a novel approach that directly distills diverse strategies through modeling across-episodic sequences. Experiments show that our algorithm achieves more efficient and stable training and has the ability to improve its behavior using historical contexts. Our code is available at https://github.com/LAMDA-RL/MED.
BibTeX
@article{Zhu_Ding_Zhang_2024, title={Multi-Expert Distillation for Few-Shot Coordination (Student Abstract)}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30539}, DOI={10.1609/aaai.v38i21.30539}, abstractNote={Ad hoc teamwork is a crucial challenge that aims to design an agent capable of effective collaboration with teammates employing diverse strategies without prior coordination. However, current Population-Based Training (PBT) approaches train the ad hoc agent through interaction with diverse teammates from scratch, which suffer from low efficiency. We introduce Multi-Expert Distillation (MED), a novel approach that directly distills diverse strategies through modeling across-episodic sequences. Experiments show that our algorithm achieves more efficient and stable training and has the ability to improve its behavior using historical contexts. Our code is available at https://github.com/LAMDA-RL/MED.}, number={21}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zhu, Yujian and Ding, Hao and Zhang, Zongzhang}, year={2024}, month={Mar.}, pages={23717-23719} }