Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tomás Lozano-Pérez
ziw@csail.mit.edu; stefje@mit.edu; lpk@csail.mit.edu; tlp@csail.mit.edu.In IEEE International Conference on Robotics and Automation (ICRA), 2017.
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.
@inproceedings{wang2017focused,
Year = {2017},
Booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
Author = {Wang, Zi and Jegelka, Stefanie and Kaelbling, Leslie Pack and Lozano-P{\'e}rez, Tom{\'a}s},
Title = {Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems}
}