Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems
Artificial Intelligence
2018-08-06 v4 Machine Learning
Robotics
Applications
Machine Learning
Abstract
We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models. It is efficient because (1) local models are estimated only when the planner requires them; (2) the planner focuses on the most relevant states to the current planning problem; and (3) the planner focuses on the most informative and/or high-value actions. Our theoretical analysis shows the validity and asymptotic optimality of the proposed approach. Empirically, we demonstrate the effectiveness of our algorithm on a simulated multi-modal pushing problem.
Cite
@article{arxiv.1607.07762,
title = {Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems},
author = {Zi Wang and Stefanie Jegelka and Leslie Pack Kaelbling and Tomás Lozano-Pérez},
journal= {arXiv preprint arXiv:1607.07762},
year = {2018}
}