Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control (Supplementary Material)

Here we summarize all our model assumptions and highlight what are learned from data. Model assumptions: The choice of coordinates: we choose which set of coordinate we want to learn and design coordinate-aware VAE accordingly. This is important from an interpretability perspective. Take the Acrobot as an example, the set of generalized coordinates that describes the time evolution of the system is not unique (see Figure 5 in [1] for another choice of generalized coordinates.) Because of this non-uniqueness, without specifying which set of coordinates we want to learn will let the model lose interpretability.