Generating Teammates for Training Robust Ad Hoc Teamwork Agents via Best-Response Diversity

Published: 24 May 2023, Last Modified: 24 May 2023Accepted by TMLREveryoneRevisionsBibTeX
Abstract: Ad hoc teamwork (AHT) is the challenge of designing a robust learner agent that effectively collaborates with unknown teammates without prior coordination mechanisms. Early approaches address the AHT challenge by training the learner with a diverse set of handcrafted teammate policies, usually designed based on an expert's domain knowledge about the policies the learner may encounter. However, implementing teammate policies for training based on domain knowledge is not always feasible. In such cases, recent approaches attempted to improve the robustness of the learner by training it with teammate policies generated by optimising information-theoretic diversity metrics. The problem with optimising existing information-theoretic diversity metrics for teammate policy generation is the emergence of superficially different teammates. When used for AHT training, superficially different teammate behaviours may not improve a learner's robustness during collaboration with unknown teammates. In this paper, we present an automated teammate policy generation method optimising the Best-Response Diversity (BRDiv) metric, which measures diversity based on the compatibility of teammate policies in terms of returns. We evaluate our approach in environments with multiple valid coordination strategies, comparing against methods optimising information-theoretic diversity metrics and an ablation not optimising any diversity metric. Our experiments indicate that optimising BRDiv yields a diverse set of training teammate policies that improve the learner's performance relative to previous teammate generation approaches when collaborating with near-optimal previously unseen teammate policies.
Submission Length: Long submission (more than 12 pages of main content)
Changes Since Last Submission: Minor Modifications: - Slightly change title to also add "Best-Response Diversity" term - Slightly change abstract to make a few sentences clearer - Add details on PLASTIC Policy parameters in appendix. - Add detailed configs for each experiment (in all environments) in codes
Supplementary Material: zip
Assigned Action Editor: ~Angeliki_Lazaridou2
License: Creative Commons Attribution 4.0 International (CC BY 4.0)
Submission Number: 790