Abstract: Embodiments described herein relate to a method and apparatus for training a model based reinforcement learning, MBRL, model for use in an environment. The method comprises obtaining a sequence of observations, ot, representative of the environment at a time t; estimating latent states st at time t using a representation model, wherein the representation model estimates the latent states st based on the previous latent states st?1, previous actions at?1 and the observations ot; generating modelled observations, om,t, using an observation model, wherein the observation model generates the modelled observations based on the respective latent states st, wherein the step of generating comprises determining means and standard deviations based on the latent states st; and minimizing a first loss function to update network parameters of the representation model and the observation model, wherein the first loss function comprises a component comparing the modelled observations, om,t to the respective observations ot.

Abstract: In a general aspect, a target is localized based on measurements from a measurement device array. In some aspects, range difference values (di) and coordinate vectors (ai) of devices in the measurement device array are obtained. The range difference values are generated based on time difference of arrival measurements of wireless signals between the target device and each of the devices in the measurement device array. A first matrix (A) and a first vector (b) are constructed. The first matrix (A) and the first vector (b) each includes the range difference values and the coordinate vectors. Whether a second vector (y) satisfies a condition set is determined. The condition set includes a first condition (ATA+?D)y=ATb and a second condition vT (ATA+?D)v?0. A numerical approximation of an optimal solution of the second vector is generated. The target device is localized according to the numerical approximation of the optimal solution.

Abstract: In a general aspect, a target is localized based on measurements from a measurement device array. In some aspects, range difference values (di) and coordinate vectors (ai) of devices in the measurement device array are obtained. The range difference values are generated based on time difference of arrival measurements of wireless signals between the target device and each of the devices in the measurement device array. A first matrix (A) and a first vector (b) are constructed. The first matrix (A) and the first vector (b) each includes the range difference values and the coordinate vectors. Whether a second vector (y) satisfies a condition set is determined. The condition set includes a first condition (ATA+?D)y=ATb and a second condition vT (ATA+?D)v?0. A numerical approximation of an optimal solution of the second vector is generated.