Focused model-learning and planning for non-Gaussian continuous state-action systems

Zi Wang; Stefanie Jegelka; Leslie Pack Kaelbling; Tomás Lozano-Pérez

ICRA 2017poster22 citations

Focused model-learning and planning for non-Gaussian continuous state-action systems

Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tomás Lozano-Pérez

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.

BibTeX

@inproceedings{icra2017_focusedmodellear,
  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},
  booktitle = {ICRA 2017},
  year = {2017}
}