Active Learning in Gaussian Process State Space Model
This work addresses the challenge of efficiently learning dynamics in state-space models for applications in physical systems, but it appears incremental as it builds on existing active learning and GPSSM methods.
The authors tackled the problem of actively steering a system to learn its underlying nonlinear dynamics using Gaussian Process state-space models, by employing mutual information as a criterion to select informative inputs, and they evaluated their approaches in several physical systems.
We investigate active learning in Gaussian Process state-space models (GPSSM). Our problem is to actively steer the system through latent states by determining its inputs such that the underlying dynamics can be optimally learned by a GPSSM. In order that the most informative inputs are selected, we employ mutual information as our active learning criterion. In particular, we present two approaches for the approximation of mutual information for the GPSSM given latent states. The proposed approaches are evaluated in several physical systems where we actively learn the underlying non-linear dynamics represented by the state-space model.