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. https://resolver.caltech.edu/CaltechAUTHORS:20170530-090151984
![]() |
PDF
- Published Version
See Usage Policy. 958kB |
![]() |
PDF
- Submitted Version
See Usage Policy. 1MB |
![]() |
Archive (ZIP)
- Supplemental Material
See Usage Policy. 1MB |
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20170530-090151984
Abstract
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: |
| |||||||||
ORCID: |
| |||||||||
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. | |||||||||
Funders: |
| |||||||||
Record Number: | CaltechAUTHORS:20170530-090151984 | |||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20170530-090151984 | |||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | |||||||||
ID Code: | 77822 | |||||||||
Collection: | CaltechAUTHORS | |||||||||
Deposited By: | George Porter | |||||||||
Deposited On: | 30 May 2017 17:16 | |||||||||
Last Modified: | 03 Oct 2019 18:02 |
Repository Staff Only: item control page