Adaptive Path-Integral Autoencoder: Representation Learning and Planning for Dynamical Systems
This work addresses representation learning and planning for dynamical systems, offering incremental improvements in inference methods for sequential data.
The authors tackled the problem of learning low-dimensional latent dynamics from high-dimensional sequential data like video, using a path-integral control-based variational inference method, resulting in tighter lower bounds for statistical model learning.
We present a representation learning algorithm that learns a low-dimensional latent dynamical system from high-dimensional \textit{sequential} raw data, e.g., video. The framework builds upon recent advances in amortized inference methods that use both an inference network and a refinement procedure to output samples from a variational distribution given an observation sequence, and takes advantage of the duality between control and inference to approximately solve the intractable inference problem using the path integral control approach. The learned dynamical model can be used to predict and plan the future states; we also present the efficient planning method that exploits the learned low-dimensional latent dynamics. Numerical experiments show that the proposed path-integral control based variational inference method leads to tighter lower bounds in statistical model learning of sequential data. The supplementary video: https://youtu.be/xCp35crUoLQ