A with Gaussian processes

This section details how P AML can be combined with Gaussian processes, as in our experiments. Alternatively, one can use other probabilistic methods, e.g., Bayesian Neural Networks [1]. Secondly, it enables mini-batch training for further improvement in computational efficiency. During the evaluation, we compute the errors with respect to the normalized outputs, since the observed environments' state representations include dimensions of differing We use control signals that alternate back and forth from one end of the range to the other to generate trajectories. This policy resulted in better coverage of the state-space, compared to a random walk.