-
Self-supervised Relational RL with Independently Controllable Subgoals
The dataset used in the paper is a multi-object environment with a robotic arm and multiple objects to manipulate. The agent learns to control the objects independently and... -
DAVIS 2017 Challenge
The DAVIS 2017 challenge dataset is a benchmark for video object segmentation. It consists of 150 sequences with multiple objects and instance-level pixel-wise annotations. -
MNIST(multi)
The MNIST(multi) dataset is used to test the ability of TARGET-VAE to identify multiple objects in images.