Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search

1 code implementation • 23 Mar 2024 • Can Bogoclu, Robert Vosshall, Kevin Cremanns, Dirk Roos

We compare trajectory sampling with density-based approximation for uncertainty propagation using three different probabilistic world models; Gaussian processes, Bayesian neural networks, and DGCNs.

Gaussian Processes Model-based Reinforcement Learning