Tag
This paper proposes a scalable local Sinkhorn divergence framework for training stochastic neural networks to reconstruct multidimensional random fields, with theoretical generalization error bounds and numerical demonstrations for uncertainty quantification.
OpenAI researchers propose a framework using stochastic neural networks for hierarchical reinforcement learning that pre-trains useful skills guided by a proxy reward, then leverages these skills for faster learning in downstream tasks with sparse rewards or long horizons.