A physics-based model prior for object-oriented mdps

One of the key challenges in using reinforcement learning in robotics is the need for models that capture natural world structure. There are meth-ods 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 ex-ploits modern simulation tools to efficiently pa-rameterize 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. 1