Learning Symbolic Models of Stochastic Domains

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 experi...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Kaelbling, L P, Pasula, H M, Zettlemoyer, L S
Format Paper Journal Article
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 10.10.2011
Subjects
Algorithms
Computer Science - Artificial Intelligence
Computer Science - Learning
Computer simulation
Domains
Machine learning
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.1110.2211