Nfnets PytorchNFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch
PbtPopulation Based Training (in PyTorch with sqlite3). Status: Unsupported
Multi object datasetsMulti-object image datasets with ground-truth segmentation masks and generative factors.
Torch GqnPyTorch Implementation of Generative Query Network
NaluBasic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units paper by trask et.al
PathnetTensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks
AllieAllie: A UCI compliant chess engine
Nfnets pytorchPre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".
Sc2aibotImplementing reinforcement-learning algorithms for pysc2 -environment
Dmc2gymOpenAI Gym wrapper for the DeepMind Control Suite
MujocounityReproducing MuJoCo benchmarks in a modern, commercial game /physics engine (Unity + PhysX).
Ml In TfGet started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Mnist EwcImplementation of ews weight constraint mentioned in recent Deep Mind paper: http://www.pnas.org/content/early/2017/03/13/1611835114.full.pdf
Pysc2 ExamplesStarCraft II - pysc2 Deep Reinforcement Learning Examples
ReaverReaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
SpriteworldSpriteworld: a flexible, configurable python-based reinforcement learning environment
Deep Learning深度学习/人工智能/机器学习资料汇总(Deep Learning/Artificial Intelligent/Machine Learning) 持续更新……
Reinforcement LearningLearn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
Alphagozero Python TensorflowCongratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th publication: [Mastering the Game of Go without Human Knowledge]. The supervised learning approach is more practical for individuals. (This repository has single purpose of education only)
reinforce-js[INACTIVE] A collection of various machine learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.
alpha-zeroAlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.
scanSCAN: Learning Abstract Hierarchical Compositional Visual Concepts
relation-networkTensorflow Implementation of Relation Networks for the bAbI QA Task, detailed in "A Simple Neural Network Module for Relational Reasoning," [https://arxiv.org/abs/1706.01427] by Santoro et. al.
muzeroA simple implementation of MuZero algorithm for connect4 game
pysc2StarCraft II Learning Environment
wavenet-classifierKeras Implementation of Deepmind's WaveNet for Supervised Learning Tasks
Pytorch-RL-CPPA Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
jax-rlJAX implementations of core Deep RL algorithms