47 Open Source Deepmind Software Projects
Free and open source deepmind code projects including engines, APIs, generators, and tools.
Andri27 Ts Reinforcement Learning 3051 ⭐
Learn Deep Reinforcement Learning in 60 days! Lectures & Code in Python. Reinforcement Learning + Deep Learning
Reaver 502 ⭐
Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo.
Conditional Pixelcnn Decoder 470 ⭐
Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network
Spriteworld 323 ⭐
Spriteworld: a flexible, configurable python-based reinforcement learning environment
Robinwho Deep Learning 322 ⭐
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……
Generative Query Network Pytorch 290 ⭐
Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"
Alphagozero Python Tensorflow 279 ⭐
Congratulation 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)
Relational Rnn Pytorch 236 ⭐
An implementation of DeepMind's Relational Recurrent Neural Networks in PyTorch.
Learning To Communicate Pytorch 211 ⭐
Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch
Visual Interaction Networks Pytorch 163 ⭐
This's an implementation of deepmind Visual Interaction Networks paper using pytorch
Visual Interaction Networks_tensorflow 133 ⭐
Tensorflow Implementation of Visual Interaction Networks
Bharathgs Nalu 110 ⭐
Basic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units paper by trask et.al
Startcraft_pysc2_minigames 109 ⭐
Startcraft II Machine Learning research with DeepMind pysc2 python library .mini-games and agents.
Advanced Deep Learning And Reinforcement Learning Deepmind 107 ⭐
🎮 Advanced Deep Learning and Reinforcement Learning at UCL & DeepMind | YouTube videos 👉
Multi_object_datasets 107 ⭐
Multi-object image datasets with ground-truth segmentation masks and generative factors.
Pathnet 94 ⭐
Tensorflow Implementation of PathNet: Evolution Channels Gradient Descent in Super Neural Networks
Recurrent Environment Simulators 73 ⭐
Deepmind Recurrent Environment Simulators paper implementation in tensorflow
Alpha Zero 54 ⭐
AlphaZero 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.
Mujocounity 48 ⭐
Reproducing MuJoCo benchmarks in a modern, commercial game /physics engine (Unity + PhysX).
Ml In Tf 45 ⭐
Get started with Machine Learning in TensorFlow with a selection of good reads and implemented examples!
Relation Network 45 ⭐
Tensorflow 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.
Overcoming Catastrophic Forgetting In Neural Networks 39 ⭐
Elastic weight consolidation technique for incremental learning.
Two Step Task 36 ⭐
Implementation of the two-step-task as described in "Prefrontal cortex as a meta-reinforcement learning system" and "Learning to Reinforcement Learn".
Pytorch Rl Cpp 35 ⭐
A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
Activeragdollassaultcourse 24 ⭐
Research into Assault Course for training Active Ragdolls (using MujocoUnity+ml_agents)
Activeragdollcontrollers 22 ⭐
Research into controllers for 2d and 3d Active Ragdolls (using MujocoUnity+ml_agents)
Neural Scene Representation And Rendering 21 ⭐
Generative Query Network for rendering 3D scenes from 2D images
Reinforce JS 18 ⭐
[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.
Neural Arithmetic Logic Units 18 ⭐
MXNet Implementation of DeepMind's Neural Arithmetic Logic Units (NALU)