Coordinated Multi-Agent Imitation Learning

Hoang M. Le, Yisong Yue, Peter Carr, Patrick Lucey
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1995-2003, 2017.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-le17a, title = {Coordinated Multi-Agent Imitation Learning}, author = {Hoang M. Le and Yisong Yue and Peter Carr and Patrick Lucey}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {1995--2003}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/le17a/le17a.pdf}, url = {https://proceedings.mlr.press/v70/le17a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Coordinated Multi-Agent Imitation Learning %A Hoang M. Le %A Yisong Yue %A Peter Carr %A Patrick Lucey %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-le17a %I PMLR %P 1995--2003 %U https://proceedings.mlr.press/v70/le17a.html %V 70 %X 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.
APA
Le, H.M., Yue, Y., Carr, P. & Lucey, P.. (2017). Coordinated Multi-Agent Imitation Learning. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:1995-2003 Available from https://proceedings.mlr.press/v70/le17a.html.

Related Material