Official repository for "Direct Advantage Estimation"

Source code and Dataset creation for the paper "Neural Symbolic Regression That Scales"

Code to implement the AND-mask and geometric mean to do gradient based optimization, from the paper "Learning explanations that are hard to vary"

Measure and visualize machine learning model performance without the usual boilerplate.

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Named Tensor implementation for Torch

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

The idea of this repository is to implement the examples and translate the book reinforcement learning by Sutton for practice. Any suggestions to improve the implementation or the translation is we…

Sum-Product Network learning routines in python

A structured list of resources about Sum-Product Networks (SPNs)

EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis (official repository)

Probabilistic line search algorithm for stochastic optimization with a TensorFlow interface.

Code for paper "L4: Practical loss-based stepsize adaptation for deep learning"