Gym Retro

A toolkit for reinforcement learning research. It is compatible with many popular reinforcement learning algorithms and implements some of the most recent deep reinforcement learning algorithms.

Expectation Maximization

Expectation Maximization (EM) is a powerful unsupervised learning algorithm that helps in clustering data with hidden variables. It is useful in identifying underlying structure of the data, and can be used in text analytics, speech recognition and object recognition.

Mask R-CNN

Mask R-CNN is an instance segmentation model used for labeling images with pixel-level accuracy.