Multi-Agent Imitation Learning with CopulasDownload PDF

28 Sept 2020 (modified: 05 May 2023)ICLR 2021 Conference Blind SubmissionReaders: Everyone
Keywords: multi-agent imitation learning, dependence modeling, copula
Abstract: Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions, which is essential for understanding physical, social, and team-play systems. However, most existing works on modeling multi-agent interactions typically assume that agents make independent decisions based on their observations, ignoring the complex dependence among agents. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents. Extensive experiments on synthetic and real-world datasets show that our model outperforms state-of-the-art baselines across various scenarios in the action prediction task, and is able to generate new trajectories close to expert demonstrations.
One-sentence Summary: In this paper, we propose a new multi-agent imitation learning algorithm by using copula to explicitly model the rich dependency structure in multi-agent systems.
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
Reviewed Version (pdf): https://openreview.net/references/pdf?id=vQvGuCQBGh
9 Replies

Loading