Search Machine Learning Repository: A Physics-Based Model Prior for Object-Oriented MDPs
Authors: Jonathan Scholz, Martin Levihn, Charles Isbell and David Wingate
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Year: 2014
Pages: 1089-1097
Abstract: One of the key challenges in using reinforcement learning in robotics is the need for models that capture natural world structure. There are, methods that formalize multi-object dynamics using relational representations, but these methods are not sufficiently compact for real-world robotics. We present a physics-based approach that exploits modern simulation tools to efficiently parameterize physical dynamics. Our results show that this representation can result in much faster learning, by virtue of its strong but appropriate inductive bias in physical environments.
[pdf] [BibTeX]

authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).