CaltechAUTHORS
  A Caltech Library Service

Generative Multi-Agent Behavioral Cloning

Zhan, Eric and Zheng, Stephan and Yue, Yisong and Sha, Long and Lucey, Patrick (2018) Generative Multi-Agent Behavioral Cloning. . (Submitted) https://resolver.caltech.edu/CaltechAUTHORS:20190205-111434225

[img] PDF - Submitted Version
See Usage Policy.

1MB

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20190205-111434225

Abstract

We propose and study the problem of generative multi-agent behavioral cloning, where the goal is to learn a generative, i.e., non-deterministic, multi-agent policy from pre-collected demonstration data. Building upon advances in deep generative models, we present a hierarchical policy framework that can tractably learn complex mappings from input states to distributions over multi-agent action spaces by introducing a hierarchy with macro-intent variables that encode long-term intent. In addition to synthetic settings, we show how to instantiate our framework to effectively model complex interactions between basketball players and generate realistic multi-agent trajectories of basketball gameplay over long time periods. We validate our approach using both quantitative and qualitative evaluations, including a user study comparison conducted with professional sports analysts.


Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription
http://arxiv.org/abs/1803.07612arXivDiscussion Paper
https://github.com/ezhan94/gen-MA-BCRelated ItemDataset
ORCID:
AuthorORCID
Yue, Yisong0000-0001-9127-1989
Additional Information:This research is supported in part by NSF #1564330, NSF #1637598, and gifts from Bloomberg, Activision/Blizzard and Northrop Grumman. Dataset was provided by STATS: https://www.stats.com/data-science/.
Funders:
Funding AgencyGrant Number
NSFIIS-1564330
NSFCCF-1637598
Bloomberg Data ScienceUNSPECIFIED
Activision/BlizzardUNSPECIFIED
Northrop GrummanUNSPECIFIED
DOI:10.48550/arXiv.1803.07612
Record Number:CaltechAUTHORS:20190205-111434225
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20190205-111434225
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:92669
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:05 Feb 2019 19:35
Last Modified:02 Jun 2023 00:39

Repository Staff Only: item control page