Replay Overshooting: Learning Stochastic Latent Dynamics with the Extended Kalman Filter
Albert H. Li,Philipp Wu,Monroe Kennedy,Albert H. Li,Philipp Wu,Monroe Kennedy
This paper presents replay overshooting (RO), an algorithm that uses properties of the extended Kalman filter (EKF) to learn nonlinear stochastic latent dynamics models suitable for long-horizon prediction. We build upon overshooting methods used to train other prediction models and recover a novel variational learning objective. Further, we use RO to extend another objective that acts as a surrog...
