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.
@article{arxiv.1110.2211,
title = {Learning Symbolic Models of Stochastic Domains},
author = {L. P. Kaelbling and H. M. Pasula and L. S. Zettlemoyer},
journal= {arXiv preprint arXiv:1110.2211},
year = {2011}
}