How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
We propose multiple methods for improving state-of-the-art GAN-based video synthesis approaches. We show that GANs using 3D-convolutions for video generation can easily be extended to predicting coherent depth maps alongside RGB frames, but results indicate that RGB accuracy does not improve if depth is available. We further propose critic-correcti...
This thesis on Artificial Intelligence for cooperative games proposes a model-free approach to learning cooperative behaviors in multi-agent reinforcement learning environments. The method encourages the emergence of cooperative policies by creating suitable environments instead of explicitly modeling the concept of cooperation itself. Various expe...