-
GAN and VAE from an Optimal Transport Point of View
The dataset used in the paper is a generative model, specifically a Wasserstein GAN and a Wasserstein VAE. -
Simple Gradient Penalty µ-WGAN Optimization Problem
The dataset used in the paper is a simple gradient penalty µ-WGAN optimization problem (SGP µ-WGAN) with a simple gradient penalty term. -
Model Imitation for Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. -
Synthetic example
The dataset is not explicitly described in the paper, but it is mentioned that the authors used a synthetic example to demonstrate the issue with the envelop theorem.
