Learning sparse relational transition models
Name
xia-iclr19.pdf
Description
Accepted version
Size
3.95 MB
Format
Unknown
Checksum (MD5)
47f0f6e3e065368d1f1d963ca6e830e4
Author(s)
Xia, Victoria F.
Wang, Zi
Allen, Kelsey Rebecca
Silver, Tom
Kaelbling, Leslie P
Date Issued
2019
Journal
7th International Conference on Learning Representations, ICLR 2019
Version
Author's final manuscript
Abstract
© 7th International Conference on Learning Representations, ICLR 2019. All Rights Reserved. We present a representation for describing transition models in complex uncertain domains using relational rules. For any action, a rule selects a set of relevant objects and computes a distribution over properties of just those objects in the resulting state given their properties in the previous state. An iterative greedy algorithm is used to construct a set of deictic references that determine which objects are relevant in any given state. Feed-forward neural networks are used to learn the transition distribution on the relevant objects' properties. This strategy is demonstrated to be both more versatile and more sample efficient than learning a monolithic transition model in a simulated domain in which a robot pushes stacks of objects on a cluttered table.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://openreview.net/forum?id=SJxsV2R5FQ
