Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2023

Abstract

Ad hoc teamwork requires an agent to cooperate with unknown teammates without prior coordination. Many works propose to abstract teammate instances into high-level representation of types and then pre-train the best response for each type. However, most of them do not consider the distribution of teammate instances within a type. This could expose the agent to the hidden risk of type confounding. In the worst case, the best response for an abstract teammate type could be the worst response for all specific instances of that type. This work addresses the issue from the lens of causal inference. We first theoretically demonstrate that this phenomenon is due to the spurious correlation brought by uncontrolled teammate distribution. Then, we propose our solution, CTCAT, which disentangles such correlation through an instance-wise teammate feedback rectification. This operation reweights the interaction of teammate instances within a shared type to reduce the influence of type confounding. The effect of CTCAT is evaluated in multiple domains, including classic ad hoc teamwork tasks and real-world scenarios. Results show that CTCAT is robust to the influence of type confounding, a practical issue that directly hazards the robustness of our trained agents but was unnoticed in previous works.

Discipline

Artificial Intelligence and Robotics | Theory and Algorithms

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of Machine Learning Research: ICML 2023, Honolulu, July 23-29

Volume

202

First Page

38272

Last Page

38285

Publisher

ML Research Press

City or Country

Cambridge

Copyright Owner and License

Authors

Additional URL

https://proceedings.mlr.press/v202/xing23a/xing23a.pdf

Download

Share

COinS