Multi-Expert Distillation for Few-Shot Coordination (Student 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.

Authors

• Yujian Zhu National Key Laboratory for Novel Software Technology, Nanjing University, China School of Artificial Intelligence, Nanjing University, China
• Hao Ding
• Zongzhang Zhang National Key Laboratory for Novel Software Technology, Nanjing University, China School of Artificial Intelligence, Nanjing University, China

Keywords

• Multiagent Learning
• Multiagent Systems
• Reinforcement Learning