Learning Symbolic Models of Stochastic Domains

Hanna M. Pasula, Luke S. Zettlemoyer, Leslie Pack Kaelbling

JAIR 2007 pp. 309-352

doi:10.1613/JAIR.2113 /jair/2007/pasula2007jair-learning/

Abstract

In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a probabilistic, relational planning rule representation that compactly models noisy, nondeterministic action effects, and show how such rules can be effectively learned. Through experiments in simple planning domains and a 3D simulated blocks world with realistic physics, we demonstrate that this learning algorithm allows agents to effectively model world dynamics.

PDF JAIR Semantic Scholar

Cite

Text

Pasula et al. "Learning Symbolic Models of Stochastic Domains." Journal of Artificial Intelligence Research, 2007. doi:10.1613/JAIR.2113

Markdown

[Pasula et al. "Learning Symbolic Models of Stochastic Domains." Journal of Artificial Intelligence Research, 2007.](https://mlanthology.org/jair/2007/pasula2007jair-learning/) doi:10.1613/JAIR.2113

BibTeX

@article{pasula2007jair-learning,
  title     = {{Learning Symbolic Models of Stochastic Domains}},
  author    = {Pasula, Hanna M. and Zettlemoyer, Luke S. and Kaelbling, Leslie Pack},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2007},
  pages     = {309-352},
  doi       = {10.1613/JAIR.2113},
  volume    = {29},
  url       = {https://mlanthology.org/jair/2007/pasula2007jair-learning/}
}