Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published August 2017 | Accepted Version + Published
Journal Article Open

Coordinated Multi-Agent Imitation Learning


We study the problem of imitation learning from demonstrations of multiple coordinating agents. One key challenge in this setting is that learning a good model of coordination can be difficult, since coordination is often implicit in the demonstrations and must be inferred as a latent variable. We propose a joint approach that simultaneously learns a latent coordination model along with the individual policies. In particular, our method integrates unsupervised structure learning with conventional imitation learning. We illustrate the power of our approach on a difficult problem of learning multiple policies for fine-grained behavior modeling in team sports, where different players occupy different roles in the coordinated team strategy. We show that having a coordination model to infer the roles of players yields substantially improved imitation loss compared to conventional baselines.

Additional Information

© 2017 the authors. This work was funded in part by NSF Awards #1564330 & #1637598, JPL PDF IAMS100224, a Bloomberg Data Science Research Grant, and a gift from Northrop Grumman.

Attached Files

Published - p1995-le.pdf

Accepted Version - 1703.03121.pdf

Accepted Version - icml2017_coordinated_long.pdf


Files (6.7 MB)
Name Size Download all
2.3 MB Preview Download
2.1 MB Preview Download
2.3 MB Preview Download

Additional details

August 19, 2023
October 17, 2023