stochastic-neural-networks

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 研究人员提出了一个使用随机神经网络进行分层强化学习的框架,该框架通过代理奖励引导预训练有用的技能,然后利用这些技能在稀疏奖励或长期视界的下游任务中加速学习。