Learning Sparse Relational Transition Models

Abstract

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.

Cite

Text

Xia et al. "Learning Sparse Relational Transition Models." International Conference on Learning Representations, 2019.

Markdown

[Xia et al. "Learning Sparse Relational Transition Models." International Conference on Learning Representations, 2019.](https://mlanthology.org/iclr/2019/xia2019iclr-learning/)

BibTeX

@inproceedings{xia2019iclr-learning,
  title     = {{Learning Sparse Relational Transition Models}},
  author    = {Xia, Victoria and Wang, Zi and Allen, Kelsey and Silver, Tom and Kaelbling, Leslie Pack},
  booktitle = {International Conference on Learning Representations},
  year      = {2019},
  url       = {https://mlanthology.org/iclr/2019/xia2019iclr-learning/}
}