Can I read Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi on EtoBox?

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi by Nekoei, Hadi; Zhao, Xutong; Rajendran, Janarthanan; Liu, Miao; Chandar, Sarath is a scholarly article available to read on EtoBox.

What is Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi about?

Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in recent years. ZSC refers to the ability of agents to coordinate zero-shot (without additional interaction experience) with independently trained agents. While ZSC is crucial for cooperative MARL agents, it might not be possible for complex tasks and changing environments. Agents also need to adapt and improve their performance with minimal interaction with other agents. In this work, we show empirically that state-of-the-art ZSC algorithms have poor performance when paired with agents trained with different learning methods, and they require millions of interaction samples to adapt to these new partners. To investigate this issue, we formally defined a framework based on a popular cooperative multi-agent game called Hanabi to evaluate the adaptability of MARL methods. In particular, we created a diverse set of pre-trained agents and defined a new metric called adaptation regret that measures the agent's ability to efficiently adapt and improve its coordination performance when paired with some held-out pool of partners on top of its ZSC performance

Author

Nekoei, Hadi; Zhao, Xutong; Rajendran, Janarthanan; Liu, Miao; Chandar, Sarath

Published

2023

Language

EN