Keywords: reinforcement learning, multi-agent reinforcement learning, agent modeling
TL;DR: A few-shot MARL approach for improving coordination ability with diverse teammates
Abstract: Coordinating with previously unknown teammates without joint learning is a crucial need for real-world multi-agent applications, such as human-AI interaction. An active research topic on this problem is ad hoc teamwork, which improves agents' coordination ability in zero-shot settings. However, previous works can only solve the problem of a single agent's coordination with different teams, which is not in line with arbitrary group-to-group coordination in complex multi-agent scenarios. Moreover, they commonly suffer from limited adaptation ability within an episode in a zero-shot setting. To address these problems, we introduce the Coordination Scheme Probing (CSP) approach that applies a disentangled scheme probing module to represent and classify the newly arrived teammates beforehand with limited pre-collected episodic data and makes multi-agent control accordingly. To achieve generalization, CSP learns a meta-policy with multiple sub-policies that follow distinguished coordination schemes in an end-to-end fashion and automatically reuses it to coordinate with unseen teammates. Empirically, we show that the proposed method achieves remarkable performance compared to existing ad hoc teamwork and policy generalization methods in various multi-agent cooperative scenarios.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)