A Caltech Library Service

Generating Long-term Trajectories Using Deep Hierarchical Networks

Zheng, Stephan and Yue, Yisong and Lucey, Patrick (2016) Generating Long-term Trajectories Using Deep Hierarchical Networks. In: Advances in Neural Information Processing Systems (NIPS 2016). Vol.3. Curran Associates , Red Hook, NY, pp. 1551-1559. ISBN 9781510838819.

[img] PDF - Published Version
See Usage Policy.

[img] PDF - Submitted Version
See Usage Policy.

[img] Archive (ZIP) - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain strategic position. Conventional policy learning approaches, such as those based on Markov decision processes, generally fail at learning cohesive long-term behavior in such high-dimensional state spaces, and are only effective when fairly myopic decision-making yields the desired behavior. The key difficulty is that conventional models are “single-scale” and only learn a single state-action policy. We instead propose a hierarchical policy class that automatically reasons about both long-term and short-term goals, which we instantiate as a hierarchical neural network. We showcase our approach in a case study on learning to imitate demonstrated basketball trajectories, and show that it generates significantly more realistic trajectories compared to non-hierarchical baselines as judged by professional sports analysts.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Yue, Yisong0000-0001-9127-1989
Additional Information:© 2016 Neural Information Processing Systems Foundation, Inc. This research was supported in part by NSF Award #1564330, and a GPU donation (Tesla K40 and Titan X) by NVIDIA.
Funding AgencyGrant Number
Record Number:CaltechAUTHORS:20170530-090151984
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:77822
Deposited By: George Porter
Deposited On:30 May 2017 17:16
Last Modified:03 Oct 2019 18:02

Repository Staff Only: item control page